Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a review from Amazon's food products. Your task is to generate a short summary of the given review in the input. Note that you don't need to write a complete sentence as a summary.\nProblem:We really like the McCann's steel cut oats but find we don't cook it up too often. This tastes much better to me than the grocery store brands and is just as convenient. Anything that keeps me eating oatmeal regularly is a good thing.\nSolution:" }, { "from": "gpt", "value": "Great taste and convenience" } ]
[ { "from": "human", "value": "Definition: You are given a sentence and your task is to generate another sentence that supports the given input.\nInput: As temperature decreases, water molecules slow down and there is a greater chance for them to condense on to surfaces.\nOutput:" }, { "from": "gpt", "value": "As the temperature of water decreases, the water molecules slow down." } ]
[ { "from": "human", "value": "Given a story, answer the question about the story. The question is the last sentence in the input. The story has one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.\nOne example is below.\nQ: Isabella entered the hall. Olivia entered the hall. Phone rang. The apple is in the blue_treasure_chest. Olivia exited the hall. Isabella moved the apple to the green_basket. Where does Isabella think that Olivia searches for the apple?\nA: blue_treasure_chest\nRationale: Since Olivia was no longer in the hall, she last remembers the apple being in the blue_treasure_chest even though Isabella moved it to the green_basket. Since Isabella was in the hall the entire time, she knows where Olivia will look for it.\nQ: Amelia entered the bathroom. Jayden entered the bathroom. The grapefruit is in the blue_suitcase. Jayden exited the bathroom. Amelia moved the grapefruit to the blue_bathtub. Phone rang. Where will Jayden look for the grapefruit?\nA:" }, { "from": "gpt", "value": "blue_suitcase" } ]
[ { "from": "human", "value": "TASK DEFINITION: Given a piece of financial news and its polarity, classify it into 'true' if the polarity is correct and classify into 'false' if the polarity is incorrect. Output must be 'true' or 'false'. \nPROBLEM: news:The value of the multi-year agreement is over EUR 2mn a year .\npolarity:neutral\n\nSOLUTION: true\n\nPROBLEM: news:( ADP News ) - Oct 29 , 2008 - Finnish lifting equipment maker Konecranes Oyj ( OMX : KCR1V ) said today that its net profit rose to EUR 116.6 million ( USD 149.1 m ) in the first nine months of 2008 from EUR 73.6 million for the s\npolarity:positive\n\nSOLUTION: true\n\nPROBLEM: news:CHS Expo Freight is a major Finnish fair , exhibition and culture logistics company that provides logistics services to various events by land , air and sea .\npolarity:negative\n\nSOLUTION:" }, { "from": "gpt", "value": "false\n\n" } ]
[ { "from": "human", "value": "Teacher: In this task, you are given a question and an answer, you would be asked to create the sentence based on the Question-Answer provided. It should be contained within the Question-Answer provided.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nQuestion: Which is an example of a renewable energy resource? Answer: Biomass\nSolution: Biomass is an example of a renewable energy resource.\nReason: The output clearly summarizes the question and answer and hence is correct\n\nNow, solve this instance: Question: What type of stratified deposit is formed where lakes are covered by ice in the winter? Answer: varves\nStudent:" }, { "from": "gpt", "value": "Varves type of stratified deposit is formed where lakes are covered by ice in the winter." } ]
[ { "from": "human", "value": "In this task, you will be given sentences and a drug name in which your task is to indicate the doses of intake of that particular drug. A dose refers to a specified amount of medication taken at one time. Although there might be several correct answers, you need to write one of them.\n\nInput: Consider Input: Three of 50 patients treated with isotretinoin (1 mg/kg/day) for cystic acne complained of poor night vision and/or excessive glare sensitivity.\t isotretinoin\n\nOutput: 1 mg/kg/day\n\n\nInput: Consider Input: Severe abdominal pain in low dosage clofazimine.\t clofazimine\n\nOutput: low\n\n\nInput: Consider Input: Temporary neurologic abnormalities were observed in one out of 23 patients undergoing chemotherapy with high-dose methotrexate (HD-MTX) for osteogenic sarcoma.\t methotrexate\n\n" }, { "from": "gpt", "value": "Output: high-dose\n\n\n" } ]
[ { "from": "human", "value": "Q: Given a sentence, fill out the missing word with a 'no' or a number (between zero and ten). You should write the numbers with english alphabet, like: four instead of 4.\nDeer show ____ symptoms of the disease.\nA:" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "The task is to generate the correct answer for a given math problem.\n\nProblem: a train overtakes two persons who are walking in the same direction in which the train is going , at the rate of 2 kmph and 4 kmph and passes them completely in 9 and 10 seconds respectively . find the length of train ?" }, { "from": "gpt", "value": "50 m" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task you will be given a list of integers. A list contains numbers separated by a comma. You need to round every integer to the closest power of 2. A power of 2 is a number in the form '2^n', it is a number that is the result of multiplying by 2 n times. The following are all powers of 2, '2, 4, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096'. If an integer is exactly in equally far from two different powers of 2 then you should output the larger power of 2. The output should be a list of integers that is the result of rounding each integer int the input list to the closest power of 2. The output should include a '[' to denote the start of the output list and ']' to denote the end of the output list.\n\n[77, 151, 4988, 2614, 11, 42, 4]\n" }, { "from": "gpt", "value": "[64, 128, 4096, 2048, 8, 32, 4]" } ]
[ { "from": "human", "value": "In this task you will be given a string of characters. You should remove all vowels from the given string. Vowels are: i,e,a,u,o. The character 'y' or 'Y' does not count as a vowel.\n\nInput: Consider Input: CXKYBDWrKayE\n\nOutput: CXKYBDWrKy\n\n\nInput: Consider Input: yIKUmumBaOueleVtb\n\nOutput: yKmmBlVtb\n\n\nInput: Consider Input: OOTNhJIiEKzdCIu\n\n" }, { "from": "gpt", "value": "Output: TNhJKzdC\n\n\n" } ]
[ { "from": "human", "value": "TASK DEFINITION: Given a story, answer the question about the story. The question is the last sentence in the input. The story has one of the three following scenarios: (1) when the individual's belief matches reality, (2) when the individual's belief does not match reality, (3) is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios.\nPROBLEM: James entered the pantry. Logan entered the pantry. The turnip is in the blue_bathtub. Logan exited the pantry. James moved the turnip to the green_treasure_chest. Where was the turnip at the beginning?\n\nSOLUTION: blue_bathtub\n\nPROBLEM: Alexander entered the laundry. Hannah entered the laundry. The pumpkin is in the blue_crate. Hannah exited the laundry. Alexander moved the pumpkin to the red_box. Alexander exited the laundry. Hannah entered the laundry. Where is the pumpkin really?\n\nSOLUTION: red_box\n\nPROBLEM: Owen entered the patio. Amelia entered the patio. The asparagus is in the green_envelope. Amelia exited the patio. Owen moved the asparagus to the blue_treasure_chest. Owen exited the patio. Amelia entered the patio. Where will Amelia look for the asparagus?\n\nSOLUTION:" }, { "from": "gpt", "value": "blue_treasure_chest\n\n" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you will be shown a conversation. You need to write a question with three choices for the conversation. Your question should be answerable based on the conversation and only have one correct answer. Note that you don't need to answer your question. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\nPart 2. Example\nW: The movie next Tuesday has been cancelled due to lack of interest. M: What do you mean? W: Well, by last night only a few tickets has been sold.\nAnswer: What can we conclude about the movie? (A) They want to buy the tickets for the movie. (B) The tickets for the movie were sold. (C) The movie will not be shown.\nExplanation: This is a good example. Based on the conversation, the movie has been canceled, and it will not be shown. We could understand that only option (C) is correct. As mentioned in the conversation, only a few tickets have been sold, so option (B) is incorrect. We don't know if they wanted to buy a ticket or not, so option (A) is incorrect as well.\nPart 3. Exercise\nWaiter: Hi. Welcome to Heavenly Pies. May I take your order? Man: Uh ... yes. I'd like the chicken fried steak. Waiter: Okay. Would you like fries, bread, or rice with your meal? Man: Umm. I'll take the rice? Waiter: Would you care for anything to drink? Man: Yeah. I'll take a medium orange juice. Waiter: I'm sorry. We only have large or small. Man: Well, in that case, uh, I'll have a small one. Waiter: Okay. A small juice. And what kind of dressing would you like with your salad. It comes with the fried steak. Man: What dressings do you have? Waiter: We have French, Italian, blue cheese, and ranch. Man: Oh! Ranch, please. Waiter: Would you like anything else? Man: Well, I'd like to see your pie menu. That's the main reason why I like to dine here. Waiter: Oh, I'm so sorry, but we aren't serving pies today. Man: Huh? I thought this was Heavenly Pies Restaurant. Waiter: Well, it usually is, but, Dave, our baker, slipped in the kitchen on a banana two days ago, and hurt his leg. [Oh] He'll be out for at least two weeks. In the meantime, we're serving ice cream sundaes instead. Sorry. Man: Wow. I'm sorry to hear that. Well in that case, I'll have an ice cream sundae. Woman: I'll be back with your order in a few minutes\nAnswer:" }, { "from": "gpt", "value": "What does the man order? (A) T-bone steak (B) chicken fried steak (C) broiled chicken" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Given a sentence, generate a most likely context or previous statement. The previous statement should be relevant to the given statement.\n\nSomeone puts off his jacket.\n" }, { "from": "gpt", "value": "He gazes at the smoldering shield, which now resembles a burning dome of flame." } ]
[ { "from": "human", "value": "Definition: Given a part of privacy policy text, identify the type of personal information which is collected, used, tracked or retained. The type of information should be present inside the given policy text, answer as 'Not Specified' otherwise\nInput: Another part of the company or institution does receive your unspecified personal information for marketing purposes. The data is personally identifiable.\nOutput:" }, { "from": "gpt", "value": "Generic personal information" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given an input text which is in one of the 11 languages listed as follows: ['Oriya' 'Malayalam' 'Bengali' 'Gujarati' 'Hindi' 'English' 'Marathi'\n 'Panjabi' 'Tamil' 'Telugu' 'Urdu']. Identify the language of input text. The input text can be in one of the given languages only. Input sentences must only have one language at a time.\n\nThe Prime Minister indicated that as India moves towards a cleaner and more fuel-efficient economy, he also wants its benefits to expand horizontally to all sections of the society, and in particular to the poorest.\nOutput:" }, { "from": "gpt", "value": "English" } ]
[ { "from": "human", "value": "Instructions: In this task, you're given an article, a question which often contains a blank and four options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer (from the given options) for the question from the given article and return one of the options from \"A\", \"B\", \"C\", and \"D\". Do not generate anything else apart from one of the following characters: \"A\", \"B\", \"C\", \"D\". There is only one correct answer for each question.\nInput: Article: With its 190 million inhabitants, Brazil has the largest population in Latin America and ranks fifth in the world. However, Brazil's population growth rate has dropped greatly and Brazilian women now have only 2.7 children on average. This achievement really becomes the envy of many other Third World countries. Brazil has become one of the developing world's great successes at reducing population growth-----but more by accident than design. While countries such as India have made joint efforts to reduce birth rates, Brazil has had a better result without really trying, says George Martine at Harvard. Martine _ , among other things, soap operas(TV series) and installment plans introduced in the 1970s. Both played an important, although indirect role in lowering the birth rate. Brazil is one of the world's biggest producers of soap operas. Globo, Brazil's most popular television network, shows three hours of soaps six nights a week, while three others show at least one hour a night. Most TV series are based on wealthy characters living the high life in big cities. \"Although they have never really tried to work in a message towards the problems of reproduction , they describe middle and upper class values-----not many children, different attitudes towards sex, women working,\" says Martine. \"They sent this image to all parts of Brazil and made people conscious of other patterns of behavior and other values, which were put into a very attractive package.\" Meanwhile, the installment plans tried to encourage the poor to become consumers. \"This led to an enormous change in consumption patterns and showed that consumption was in contradiction with unlimited reproduction,\" says Martine. \n Question: According to the passage, many Third World countries _ . \n Options: (A) haven't attached much importance to birth control (B) would soon join Brazil in controlling their birth rate (C) neglected the role of TV plays in family planning (D) haven't yet found effective measures to control their population\nOutput:" }, { "from": "gpt", "value": "D" } ]
[ { "from": "human", "value": "Instructions: In this task, we ask you to write an answer to a question about the events that may happen before or after a certain event. For example, \"earning money\" usually appears before \"spending money\". Note that a lot of the questions could have more than one correct answer. We only need a single most-likely answer. Please try to keep your \"answer\" as simple as possible. Concise and simple \"answer\" is preferred over those complex and verbose ones.\nInput: Sentence: I suppose he was attracted to the commotion up the hill.\". \nQuestion: What did he do after he was attracted?\nOutput:" }, { "from": "gpt", "value": "he ran up the hill." } ]
[ { "from": "human", "value": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to output the first i elements of A, starting with the 1st element in A. i will always have a value less than the length of A\n--------\nQuestion: 2, ['k', '6189', 'P', 'a']\n\nAnswer: k, 6189\n\n\nQuestion: 11, ['8369', 'v', '2079', '1537', '2227', 'E', '7867', 'g', 'l', 'd', '9543', '5931', '35', '475', 'S', '7071', '2979', 'S', '6137', 'n', '6529', '1979', '5035']\n\nAnswer: 8369, v, 2079, 1537, 2227, E, 7867, g, l, d, 9543\n\n\nQuestion: 4, ['Q', '6081', '8505', 'E', '1673', '2965', '2047', 'j', '2125', '6341', '4731', '6369', '4721']\n\nAnswer:" }, { "from": "gpt", "value": "Q, 6081, 8505, E\n\n\n" } ]
[ { "from": "human", "value": "In this task, you are given an input list A comprising of numbers and alphabets. You need to extract and sort the unique alphabets in the list. The alphabets in the input list will only be in lowercase. Return -1 if there is no alphabet in the input list.\nOne example is below.\nQ: ['8129', 'a', '4245', 'y', 'm', 'a']\nA: a, m, y\nRationale: Here, the unique alphabets in the list are 'a', 'y', and 'm', hence their sorted order is 'a, m, y'.\nQ: ['k', '3171', 'i', '6951', 'j', '7467', 'q', 'z', '4121', 'z', '2853', '3927', '6259', 't', 'x', 'h', 'e', '1803', '9767', '2275', 'h', 't', 'a', '9251', 'j', 'o', '5111', 't', '7725', 'f', 'c', 'q', '7819', '8889', '6309', '9981', '7765', 'y']\nA:" }, { "from": "gpt", "value": "a, c, e, f, h, i, j, k, o, q, t, x, y, z" } ]
[ { "from": "human", "value": "Detailed Instructions: The input is taken from a negotiation between two participants who take the role of campsite neighbors and negotiate for Food, Water, and Firewood packages, based on their individual preferences and requirements. Given an utterance and recent dialogue context containing past 3 utterances (wherever available), output Yes if the utterance contains the other-need strategy, otherwise output No. other-need is a selfish negotiation strategy. It is used when the participants discuss a need for someone else rather than themselves. For instance, describing the need for firewood to keep the kids warm.\nQ: Context: 'i think i should have 2 waters because i will need to put the fire out to protect the forest.' 'Well, if we can't settle on an agreement i'm going to walk away. We agreed I will get all 3 extra packages of the food but I still wish for the 2 extra wood and 2 extra waters' 'no we agree that you would get 3 food, i would get 3 waters'\nUtterance: 'It's agreed, I will get 3 extra packs of food, you will get 3 waters but the extra wood for my kids is needed how about I get 2 extra firewood?'\nA:" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "Q: In this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story incoherent / implausible by indicating 1 or 2 in the output. If both sentences are plausible, pick the one that makes less sense.\nBeginning: I always try to close my chicken coop just before dark. Middle 1: My chicken is always in the coop by dark. Middle 2: Sometimes my chicken isn't in there before dark. Ending: I always have to wait to close the coop when she is ready.\nA:" }, { "from": "gpt", "value": "1" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. You are given a target profession, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.\n\nTarget: musician \nMy boyfriend is a musician but hasn't been able to perform. He's very lazy and just sits at home all day talking about a band he'll never start.\n" }, { "from": "gpt", "value": "stereotype" } ]
[ { "from": "human", "value": "You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. If the conversation begins with a question, label it '1' otherwise '0'.\nExample: Person1: Passport , please , madam . \n Person2: Just a minute , please . It's in my bag . Here it is . \n Person1: Thank you . Please fill out the Baggage Declaration Form . \n Person2: All right . Shall I enter all my belongings ? \n Person1: No , only the articles listed on the Declaration . \nExample solution: 0\nExample explanation: The first sentence in the conversation begins with a request, therefore there is no presence of a question.\n\nProblem: Person1: Shall we have some soup first ? \n Person2: No , thank you . I don't like soup . I'd rather have some fruit juice to start with . \n Person1: Ok , and what about the main course ? Which would you rather have fish or meat ? \n Person2: Meat , I think . \n Person1: Don't you like fish then ? \n Person2: I do , but I want meat . \n Person1: Shall we have some white wine then ? \n Person2: Yes , but I prefer red wine with meat . \n Person1: What would you like for dessert ? \n Person2: I just want to have a coffee , I think . \n Person1: Fine , and after dinner , shall we go to a disco ? \n Person2: No , thanks . I'd like to go straight home . I'm very tired . \n" }, { "from": "gpt", "value": "Solution: 0" } ]
[ { "from": "human", "value": "Part 1. Definition\nYou will be asked how to do a certain task. You should describe a physical process that does not lead to the asked outcome, yet it is closely related to it (i.e., it should use the words that are provided in the input). The physical process can be moving something, arranging something in a certain way, mixing things, shaking them, etc. To make sure that the generated process does not lead to the asked outcome, you can introduce objects or events unrelated to the context of the question e.g. 'cleaning the keyboard by making an elephant sit on them'; or you can create contradictory statements e.g. 'drying wet keyboards with running water'. In your responses, avoid typos and misspellings.\nPart 2. Example\nHow do you remove keys from a computer keyboard for cleaning?\nAnswer: Place the tip of your finger under the corner of a key and gently twist to pop it off.\nExplanation: The answer is related to the question, but certainly doesn't lead to the asked outcome( A sharp narrow object should be used instead of finger.), so this is a correct answer.\nPart 3. Exercise\nstop rust on garden furniture\nAnswer:" }, { "from": "gpt", "value": "mix a batch of bloody mary mix, and add vodka. dip a clean toothbrush in the mixture, and rub on the furniture. rinse well." } ]
[ { "from": "human", "value": "\"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). Given a prompt and two responses, identify which response is the type of \"yes, and\". Indicate your answer by 'Response 1' if the first response is correct, otherwise 'Response 2'. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange.\nOne example is below.\nQ: Prompt: See, Arlene? That's why I don't talk to you like that because I'm afraid I'll scare our son. \n Response 1: I have 12. Wait, is the key to a success story getting the number to go down? \n Response 2: Oh, Dad. Even that wasn't great.\nA: Response 2\nRationale: Response 2 is correct answer because it agrees with the prompt and continues the conversation in the same context.\nQ: Prompt: You see, he makes like he's in a box. Now he's walking against the wind. \n Response 1: That sounds good. Just make sure you get us a good player in return. \n Response 2: But you told me you were pickpockets. So you're also theater students?\nA:" }, { "from": "gpt", "value": "Response 2" } ]
[ { "from": "human", "value": "In this task, you are given a sentence and a question, you would be asked to create the answer which is contained in the sentence provided.\nQ: Sentence: Nuclear energy is released when the nucleus of an atom is split. Question: What kind of energy is released when the nucleus of an atom is split?\nA: " }, { "from": "gpt", "value": "nuclear" } ]
[ { "from": "human", "value": "Definition: In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the count of all the alphabetical elements in the given list. Return 0 if no alphabetical element in the list\nInput: ['G', '6507', '3689', 's', '4231', '3227', '795', '5991', 'r', 'h', '5303', 's', '745', '4687', 'r', 'Q', 'c', 'N', '8223', '6611', 'Q', 'A', 'T', 'H', 'n', '9259', 'Y', '5049', '5167', '7285', 'B', 'y', '7377', 'X', 'V', 'O', '345']\nOutput:" }, { "from": "gpt", "value": "20" } ]
[ { "from": "human", "value": "instruction:\nIn this task you need to indicate the plausibility of reasoning for the pronoun coreference relations. Each of the provided inputs contains a sentence with a target pronoun and a sentence that justifies which noun phrase the pronoun refers to. Correct reasons do not need to use all the knowledge from the sentence. The resolution of the pronoun coreference relations typically involve one or multiple following knowledge types about commonsense: First: 'Property', the knowledge about property of objects (e.g., ice is cold). Second: 'Object', the knowledge about objects (e.g., cats have ears). Third: 'Eventuality', the knowledge about eventuality (e.g., 'wake up' happens before 'open eyes'). Forth: 'Spatial', the knowledge about spatial position (e.g., object at the back can be blocked). Fifth: 'Quantity', the knowledge about numbers (e.g., 2 is smaller than 10). Sixth: all other knowledge if above ones are not suitable. You should answer 'Correct' if the reasoning made sense, otherwise, you should answer 'Wrong'.\nquestion:\nSentence: The firemen arrived before the police because they were coming from so far away.\n Reason: The 'they' refers to the police because only the police could have pulled the firemen out of the burning building. \n Question: Is the above reasoning correct or wrong? \nanswer:\nWrong\n\n\nquestion:\nSentence: The trophy doesn't fit into the brown suitcase because it is too small.\n Reason: The 'it' refers to the suitcase because a suitcase is a holder for the trophy item. \n Question: Is the above reasoning correct or wrong? \nanswer:\nCorrect\n\n\nquestion:\nSentence: If the con artist has succeeded in fooling Sam, he would have lost a lot of money.\n Reason: The 'he' refers to sam because people do not lose money for fooling people. \n Question: Is the above reasoning correct or wrong? \nanswer:\n" }, { "from": "gpt", "value": "Correct\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: Here are two questions (Question1 and Question2). If these questions have the same meaning and same answer, answer \"Yes\", otherwise \"No\".\nProblem:Question1: What is the future of front end developer?, Question2: What is the future of Front End Developers?\nSolution:" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured.\nExample: [['Northwestern College', 'NICKNAME', 'Red Raiders'], ['Northwestern College', 'LOCATION', 'Orange City, Iowa']]\nOutput: The team whose nickname is red raiders is located in the orange city, iowa\nThis sentence uses the triplets by correctly using the (subject, predicate, object) semantics for both the triplets provided. Since college teams are popularly associated with nicknames, some information in the generated sentence can be inferred. In this case, Northwestern College was replaced with the team automatically.\n\nNew input case for you: [['The Wrestlers', 'eatType', 'pub'], ['The Wrestlers', 'food', 'French'], ['The Wrestlers', 'priceRange', 'cheap'], ['The Wrestlers', 'area', 'riverside'], ['The Wrestlers', 'familyFriendly', 'yes'], ['The Wrestlers', 'near', 'Raja Indian Cuisine']]\nOutput:" }, { "from": "gpt", "value": "The Wrestlers is a cheap family friendly French pub and a coffee shop located near Raja Indian Cuisine near riverside" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven a trivia question, classify broad topical category from this list: 'theater', 'geology', 'book', 'tv', 'astronomy', 'aviation', 'military', 'government', 'boxing', 'projects', 'metropolitan_transit', 'law', 'venture_capital', 'broadcast', 'biology', 'people', 'influence', 'baseball', 'spaceflight', 'media_common', 'cvg', 'opera', 'olympics', 'chemistry', 'visual_art', 'conferences', 'sports', 'language', 'travel', 'location', 'award', 'dining', 'martial_arts', 'comic_strips', 'computer', 'user', 'tennis', 'music', 'organization', 'food', 'event', 'transportation', 'fictional_universe', 'measurement_unit', 'meteorology', 'distilled_spirits', 'symbols', 'architecture', 'freebase', 'internet', 'fashion', 'boats', 'cricket', 'film', 'medicine', 'finance', 'comic_books', 'celebrities', 'soccer', 'games', 'time', 'geography', 'interests', 'common', 'base', 'business', 'periodicals', 'royalty', 'education', 'type', 'religion', 'automotive', 'exhibitions'.\n\nWhich Welsh singer was born Gaynor Hopkins?\nOutput:" }, { "from": "gpt", "value": "common" } ]
[ { "from": "human", "value": "In this task, you need to count the number of times the given letter appears in the given sentence.\nQ: Sentence: 'a pink, white and blue bus is by a small building'. Find frequency of the letter 'd'\nA: " }, { "from": "gpt", "value": "2" } ]
[ { "from": "human", "value": "In this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every odd number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no odd numbers in an inner list you should output 0 for that list.\nQ: [[29, -48], [45, -26, -5], [40, 39, -8, 18], [-4, -43, -20], [-37, -2, 21, -33, -43], [-31, -36, 33, -22], [25, -12, 11], [-7, -31, -3, -23, -27], [-22, -46, -20, -25, -30], [16, -1, 20], [-41, -50, -12]]\nA: " }, { "from": "gpt", "value": "[29, -225, 39, -43, -1102563, -1023, 275, -404271, -25, -1, -41]" } ]
[ { "from": "human", "value": "In this task, you are given a question, and your task is to predict the context of the question. We assume that someone named X asked the question from Y. The context of the question means the previous situation that led X to ask this question.\n\n[EX Q]: Do you still live with your mom?\n[EX A]: X and Y are childhood neighbours who unexpectedly run into each other at a cafe.\n\n[EX Q]: Are you a fan of mountain climbing?\n[EX A]: X wants to know what activities Y likes to do during weekends.\n\n[EX Q]: Do you like to read?\n[EX A]:" }, { "from": "gpt", "value": "Y has just moved into a neighbourhood and meets his/her new neighbour X.\n\n" } ]
[ { "from": "human", "value": "Q: In this task, you are given a sentence that is either in the Yoruba language or the English language. Your task is to identify the language of the input sentence. Input sentences should be in Yoruba or English language and also it cannot have two languages at a time.\nThe task one takes on waking in the morning does not flounder.\nA:" }, { "from": "gpt", "value": "English" } ]
[ { "from": "human", "value": "Instructions: In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.\nInput: How many wins on the PGA tour does the winner of the 2010 LPGA State Farm Classic have ?\nOutput:" }, { "from": "gpt", "value": "20" } ]
[ { "from": "human", "value": "Part 1. Definition\nYou will be given a context and a verb separated with a newline character. You have to identify if the given verb implies an opinion, an intention, a wish or not. Please note that a verb refers to an intention only if it refers to an event planned to happen in the future and is not conditional (or part of a condition). The output should be: 'Yes' if the verb refers to an opinion, an intention, or a wish; and 'No' otherwise.\nPart 2. Example\nIt was followed by Denmark, Norway, Germany, France, Greece, Luxembourg, Spain, Britain, the United States, Iceland, Belgium, Italy, Portugal and Turkey. NATO decided at last year's Madrid summit to (invite) the three eastern European countries to start accession talks. \n Verb: invite\nAnswer: Yes\nExplanation: They planned to \"invite\" the three eastern European countries, so this verb refers to an intention.\nPart 3. Exercise\n( 0735 GMT ) Friday, toppling a crowded building toward the embassy and a street packed with cars, trucks and buses. At least 75 people were killed and 1,643 wounded there, Red Cross and ambulance officials (said). \n Verb: said\nAnswer:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Instructions: In this task, you are given a short passage that may convey stereotype, anti-stereotype, or is unrelated. A stereotype is an over-generalized belief about a particular group of people. An anti-stereotype is an idea that goes against a common stereotype. The passage is unrelated if it does not convey a stereotype or anti-stereotype. You are expected to classify the passage into three classes: stereotype, anti-stereotype, and unrelated.\nInput: Passage: Spain has good weather. They have hot tempers.\nOutput:" }, { "from": "gpt", "value": "Stereotype" } ]
[ { "from": "human", "value": "In this task, you will be presented with a question in Dutch language, and you have to write the named entities from the question if present. B denotes the first item of a phrase and an I any non-initial word. Here is the list of terms used: person names (PER), organizations (ORG), locations (LOC) and miscellaneous names (MISC). There can be instances with no named entities, then return 'None'.\n\nMet de opvolger , die ondertussen al in de toonzalen van het merk staat , wordt op veel hogere verkoopcijfers gemikt ." }, { "from": "gpt", "value": "None" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nGiven a statement about date and time, state whether the statement is true or false. The number of date/time operands in the statement ranges between 2 and 3. Let's say the values are denoted by t1, t2 and t3. The statements follow one of the following ten templates: 't1 occurs before t2, t1 doesn't occur before t2, t1 occurs after t2, t1 doesn't occur after t2, t1 occurs between t2 and t3, t1 doesn't occur between t2 and t3, t1 occured before t2 but after t3, t1 occured after t2 but before t3, t1 didn't occur before t2 but after t3, t1 didn't occur after t2 but before t3'. The output should be either 'True' or 'False'.\n\n03:40:40 PM doesn't occur between 5:35:38 and 07:58:59 AM\nSolution: False\nWhy? The output of 'False' is correct as the input statement is false, since 03:40:40 PM occurs after 07:58:89 AM and not between 5:35:38(AM) and 07:58:59 AM\n\nNew input: 05:39:36 PM occured before 10:12:35 but after 2:35:09\nSolution:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. There are several possible answers, you'll need to choose the proper one. Carefully read the given text, pay special attention to the marked number, think about what (unwritten) information the marked number holds inside, choose the most adequate word(s) from the optional answers. If none of them seems right to you, there's also an option for other. If your answer is \"REFERENCE\", also write the reference entity, otherwise write the implicit option name. Options to choose from are:\nREFERENCE: Some object which is being mentioned in the text before or after the target number. The reference answer has a higher priority than any other. If both Reference and another answer are possible, prioritize the Reference.\nYEAR: Describing a calendric year\nAGE: Describing someone's age\nCURRENCY: Reference to some monetary value e.g dollar, euro etc.\nPEOPLE: Describing a single/plural persons\nTIME: Describing a time of the day. Usually you can add the word o'clock after those numbers.\nOTHER: Some other option, which isn't listed here.\nQ: Stan Hooper: Hey , Molly , listen to this _ one _ : Your minute last week really made me think about my life , God bless you Stan Hooper . That 's why I work so hard on those little essays , you know , make a difference .\nMolly Hooper: What was your minute last week ?\nStan Hooper: Eh , who remembers , ah , send him an eight by ten there , ah .\nMolly Hooper: Color or black & white ?\nStan Hooper: Color , I changed the man 's life .\nMolly Hooper: He did n't say you changed it , he said you made him think about it .\nStan Hooper: Oh yeah , you 're right . Black & white .\nA: " }, { "from": "gpt", "value": "OTHER" } ]
[ { "from": "human", "value": "In this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every even number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no even numbers in an inner list you should output 0 for that list.\nOne example: [[7, -3, -3, 11], [-6, -6, -5, 2], [-8, 4, -3]]\nSolution is here: [0, 72, -32]\nExplanation: The first inner list has no even integers, so the first number in the output is 0. The second list has -6, -6, 2 for even integers so the second output is 72. The third list has -8, 4 as even numbers so the third output is -32. This is a good example.\n\nNow, solve this: [[10, 18, -39], [-33, 40], [24, -50, 31]]\nSolution:" }, { "from": "gpt", "value": "[180, 40, -1200]" } ]
[ { "from": "human", "value": "Detailed Instructions: You will be given a piece of text either about an everyday event, or a general statement. If the event seems a plausible event to you, or the general statement makes sense matches your commonsense, output 'True', otherwise output 'False'.\nSee one example below:\nProblem: The glass fell of a three-story building, so it broke into pieces.\nSolution: True\nExplanation: Falling down from a considerable height causes glasses to break, so this is a true sentence.\n\nProblem: Since some time is reserved for commercials, the hour-long TV program lasts less than 60 minutes.\nSolution:" }, { "from": "gpt", "value": "True" } ]
[ { "from": "human", "value": "Instructions: In this task, you are given a paragraph (from a research paper) and your task is to classify each sentence of the paragraph (assume n sentence) into the following categories: Background, Purpose, Method, Finding/Contribution, or Other. Return the output in this format: 1 - category of sentence 1, 2 - category of sentence 2, ..., n - category of sentence n; where each number indicates the order of the sentence. The categories can be identified using the following questions: \n Background: - Why is this problem important? - What relevant works have been done before? - What did the previous works miss? - What are the high-level research questions? - How might this help other researchers?\n Purpose: - What specific things do the researchers want to do? - What specific knowledge do the researchers want to know? - What specific hypothesis do the researchers want to test?\n Method: - How did the researchers do it or find it out? - What are the procedures and steps of this research?\n Finding/Contribution: - What did the researchers find out? Did the proposed methods work? - Did things behave as the researchers expected?\nOther: put every text fragment that does not fit into any of the categories above here. Put a sentence here if its not in English, is not part of the article, contains numbers and dates, is a caption of a figure or a table, is a formatting error, or you are not sure about it.\nInput: Objectives of this study were to determine prevalence of infection in feral cats in Northern Florida with a select group of infectious organisms and to determine risk factors for infection. Blood samples or sera from 553 cats were tested with a panel of antibody, antigen or PCR assays. Male cats were at higher risk for FIV, Mycoplasma haemofelis, and M. haemominutum. Infection with either FeLV or FIV was associated with increased risk for coinfection with the other retrovirus, M. haemofelis, or M. haemominutum. Bartonella henselae had the highest prevalence and was the only organism that did not have any associated risk for coinfection with other organisms. Feral cats in this study had similar or lower prevalence rates of infections than those published for pet cats in the United States. Thus, feral cats assessed in this study appear to be of no greater risk to human beings or other cats than pet cats.\nOutput:" }, { "from": "gpt", "value": "1 - purpose, 2 - method, 3 - finding, 4 - finding, 5 - finding, 6 - finding, 7 - finding, 8 - finding, 9 - finding" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you're given a paragraph from the research paper and your task is to generate a suitable title for the research paper based on the given paper. Under 100 words is a good title length.\n\nThe severe acute respiratory syndrome (SARS) epidemic originating from China in 2002 was caused by a previously uncharacterized coronavirus that could be identified by specific RT-PCR amplification. Efforts to control future SARS outbreaks depend on the accurate and early identification of SARS-CoV infected patients. A real-time fluorogenic RT-PCR assay based on the 3 -noncoding region (3 -NCR) of SARS-CoV genome was developed as a quantitative SARS diagnostic tool. The ideal amplification efficiency of a sensitive SARS-CoV RT-PCR assay should yield an E value (PCR product concentration increase per amplification cycle) equal to 2.0. It was demonstrated that the 3 -NCR SARS-CoV based RT-PCR reactions could be formulated to reach excellent E values of 1.81, or 91% amplification efficacy. The SARS-CoV cDNA preparations derived from viral RNA extract and the cloned recombinant plasmid both exhibit the identical amplification characteristics, i.e. amplification efficacy using the same PCR formulation developed in this study. The viral genomic copy (or genomic equivalences, GE) per infectious unit (GE/pfu) of SARS-CoV used in this study was also established to be approximate 1200-1600:1. The assay's detection sensitivity could reach 0.005 pfu or 6-8 GE per assay. It was preliminarily demonstrated that the assay could efficiently detect SARS-CoV from clinical specimens of SARS probable and suspected patients identified in Taiwan. The 3 -NCR based SARS-CoV assay demonstrated 100% diagnostic specificity testing samples of patients with acute respiratory disease from a non-SARS epidemic region.\nSolution: Development and evaluation of an efficient 3 -noncoding region-based SARS coronavirus (SARS-CoV) RT-PCR assay for detection of SARS-CoV\nWhy? It's a correct title because the paragraph described the development of 3 -noncoding region of SARS-CoV genome and assay efficiently detecting SARS-CoV from clinical specimens.\n\nNew input: Determining the factors that influence the transmission of parasites among hosts is important for directing surveillance of animal parasites before they successfully emerge in humans, and increasing the efficacy of programs for the control and management of zoonotic diseases. Here we present a review of recent advances in the study of parasite sharing, wildlife ecology, and epidemiology that could be extended and incorporated into proactive surveillance frameworks for multi-host infectious diseases. These methods reflect emerging interdisciplinary techniques with significant promise for the identification of future zoonotic parasites and unknown reservoirs of current zoonoses, strategies for the reduction of parasite prevalence and transmission among hosts, and decreasing the burden of infectious diseases.\nSolution:" }, { "from": "gpt", "value": "The study of parasite sharing for surveillance of zoonotic diseases" } ]
[ { "from": "human", "value": "A question is presented to you in this task, and your job is to write a potentially correct answer.\nOne example is below.\nQ: where did france surrender ww2?\nA: Mediterranean Sea\nRationale: This is a good example and the output correctly answers the question.\nQ: who is john cabot's parents?\nA:" }, { "from": "gpt", "value": "Guilo Caboto" } ]
[ { "from": "human", "value": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n\| Attribute \| triggerword \| contrastive triggerword \| \n\| age \| old \| new \| \n\| altitude \| low \| high \|\n\| area \| small \| vast \| \n\| brightness \| dark \| light \| \n\| clarity \| obscure \| clear \| \n\| cleanness \| dirty \| clean \| \n\| complexity \| simple \| complex \| \n\| cost \| cheap \| expensive \|\n\| density \| sparse \| dense \|\n\| depth \| shallow \| deep \|\n\| distance \| near \| far \| \n\| electric conductivity \| low \| high \|\n\| flexibility \| rigid \| flexible \|\n\| granularity \| fine \| coarse \| \n\| hardness \| soft \| hard \| \n\| length \| short \| long \| \n\| magnitude \| small \| large \| \n\| mass \| small \| large \| \n\| odor \| weak \| strong \| \n\| pressure \| low \| high \| \n\| resistance \| low \| high \| \n\| shape \| round \| sharp \|\n\| shape \| flat \| spiky \|\n\| size \| small \| large \| \n\| sound \| quiet \| loud \| \n\| sound pitch \| low \| high \| \n\| speed \| slow \| fast \| \n\| stability \| unstable \| stable \| \n\| strength \| weak \| strong \| \n\| temperature \| low \| high \| \n\| texture \| smooth \| rough \| \n\| thermal conductivity \| low \| high \|\n\| thickness \| thin \| thick \| \n\| volume \| small \| large \|\n\| weight \| light \| heavy \| \n\| width \| narrow \| wide \| \n\| location \| in \| out \|\n\| location \| up \| down \|\n\| location \| above \| below \|\n\| location \| on \| off \|\n\| location \| to \| from \|\n\n\nInput: Consider Input: Context Word: eyebrows. \nQuestion: The woman highlighted her eyebrows but not her hair for the ceremony because she wanted the _ to stand out. \nAnswer: eyebrows.\n\nOutput: The woman highlighted her eyebrows but not her hair for the ceremony because she wanted the _ to blend in.\n\n\nInput: Consider Input: Context Word: therapy. \nQuestion: The therapy that I had extended past the timeframe because the _ was very intense. \nAnswer: therapy.\n\nOutput: The therapy that I had extended past the timeframe because the _ was very little.\n\n\nInput: Consider Input: Context Word: celebrate. \nQuestion: More people were there to celebrate the wedding than the reunion because the _ was held at a bigger venue. \nAnswer: wedding.\n\n" }, { "from": "gpt", "value": "Output: More people were there to celebrate the wedding than the reunion because the _ was held at a smaller venue.\n\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to generate a natural language interpretation of the given command. \n Here are the definitions of logical operators: \n 1. count: returns the number of rows in the view \n 2. only: returns whether there is exactly one row in the view \n 3. hop: returns the value under the header column of the row \n 4. and: returns the boolean operation result of two arguments \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column \n 6. nth max/nth min: returns the n-th max/n-th min of the values under the header column \n 7. argmax/argmin: returns the row with the max/min value in header column \n 8. nth argmax/nth argmin: returns the row with the n-th max/min value in header column \n 9. eq/not eq: returns if the two arguments are equal \n 10. round eq: returns if the two arguments are roughly equal under certain tolerance \n 11. greater/less: returns if argument 1 is greater/less than argument 2 \n 12. diff: returns the difference between two arguments \n 13. filter eq/not eq: returns the subview whose values under the header column is equal/not equal to argument 3 \n 14. filter greater/less: returns the subview whose values under the header column is greater/less than argument 3 \n 15. filter greater eq /less eq: returns the subview whose values under the header column is greater/less or equal than argument 3 \n 16. filter all: returns the view itself for the case of describing the whole table \n 17. all eq/not eq: returns whether all the values under the header column are equal/not equal to argument 3 \n 18. all greater/less: returns whether all the values under the header column are greater/less than argument 3 \n 19. all greater eq/less eq: returns whether all the values under the header column are greater/less or equal to argument 3 \n 20. most eq/not eq: returns whether most of the values under the header column are equal/not equal to argument 3 \n 21. most greater/less: returns whether most of the values under the header column are greater/less than argument 3 \n 22. most greater eq/less eq: returns whether most of the values under the header column are greater/less or equal to argument 3\n\neq { hop { nth_argmax { all_rows ; attendance ; 3 } ; competition } ; danish superliga 2005 - 06 } = true\nSolution: select the row whose attendance record of all rows is 3rd maximum. the competition record of this row is danish superliga 2005-06.\nWhy? Here, the generated sentence interprets given logical form correctly that 3rd maximum should be selected from given table rows.\n\nNew input: eq { count { filter_eq { filter_eq { all_rows ; laps ; 334 } ; manufacturer ; chevrolet } } ; 2 } = true\nSolution:" }, { "from": "gpt", "value": "select the rows whose laps record is equal to 334 . among these rows , select the rows whose manufacturer record fuzzily matches to chevrolet . the number of such rows is 2 ." } ]
[ { "from": "human", "value": "Part 1. Definition\nYou are given a paragraph, with numbered sentences, and a question. Write the numbers of the sentences needed to answer the given question. Separate multiple sentence numbers with a comma (\", \"). E.g. \"1, 2\" would be the correct response if Sent 1 and Sent 2 are needed to answer the given question (do not include sentences that contain no information that is necessary to answer the question). Sort the sentence numbers in an increasing order (i.e., '1, 2', instead of '2, 1'). Your answer should not contain anything than the sentence numbers separated by a comma (e.g. '1, 2, 3, 4'). The given question requires more than one sentence to answer. So, your answer must contain at least one comma (\", \").\nPart 2. Example\nParagraph- Sent 1: A Republican bid to keep the government open past Friday includes no new money for the construction of a border wall along the U.S.-Mexico border, according to several congressional aides familiar with ongoing talks.\nSent 2: GOP leaders submitted the new offer Tuesday afternoon in an effort to appease Democrats, whose votes are needed to avert a shutdown of federal agencies, several House and Senate aides said.\nSent 3: However, Republicans also insisted on increases in border security and defense spending, including money to repair existing fencing and new surveillance technology to patrol the nearly 2,000-mile border.\nSent 4: Democrats have indicated that they would support such appropriations so long as no money goes toward an actual wall.\nQuestion: Who has to be appeased to keep the government open?.\nAnswer: 1, 2.\nExplanation: The question is: Who has to be appeased to keep the government open? The phrase \"appease Democrats\" is mentioned in Sent 2, about accepting offer that is mentioned in Sent 1 to \"keep the government open\". So, Sent 1 and Sent 2 are the sentences needed to answer this question.\nPart 3. Exercise\nParagraph- Sent 1: Historically, LSEO letter-writing campaigns generated from $11,000 to $25,000 annually, recalls Dallas Ferguson, a Tulsa attorney and board president of the new LASO.\nSent 2: That amount hardly offset enormous cuts, beginning in 1996, by Congress to Legal Services Corp., the chief funding source for state legal-aid agencies.\nSent 3: Threatened with extinction, LSEO clawed its way back with the help of state funding, grant money and the Tulsa Area United Way.\nSent 4: Meanwhile, the clients keep coming.\nSent 5: At least three-quarters are women and children living in poverty.\nSent 6: The agency helps more than 12,000 children a year.\nSent 7: A third of LSEO's clients are the working poor who receive no government benefits.\nSent 8: Many are senior citizens.\nSent 9: Riggs regrets that retired Tulsa attorney John Athens, a champion of legal aid, did not live to see how much the money has meant.\nSent 10: Athens died last year.\nSent 11: In his honor, The Oxley Foundation donated $200,000 to expand a client hot line.\nSent 12: That service, which will be expanded statewide, enables needy people to consult an attorney about civil legal problems, including rent and contract disputes, domestic abuse, consumer issues and custody matters.\nSent 13: Attorneys handle no criminal cases.\nSent 14: R.H. Harbaugh, foundation trustee and a colleague of Athens at the Conner & Winters law firm, said his mentor had \"a special interest in people who could not afford legal services.\nSent 15: He was aware of the hot line and supported its expansion.\"Sent 16: Said Riggs: \"We use lofty phrases such as 'with justice for all,' when we talk about our legal system.\nSent 17: That phrase is etched on our U.S. Supreme Court building.\nSent 18: Those are just empty words if people don't have access to that system.\". \nQuestion: What agency helps more than 12,000 children a year?.\nAnswer:" }, { "from": "gpt", "value": "3, 6." } ]
[ { "from": "human", "value": "Given a scientific passage and an answer, generate a question for the given answer.\n\n[EX Q]: Passage: Images in a plane mirror are reversed left and right but not reversed top and bottom. Answer: plane mirror\n[EX A]: Images in what type of mirror are reversed left and right but not reversed top and bottom?\n\n[EX Q]: Passage: Viruses , like the one depicted in Figure below , are tiny particles that may cause disease. Human diseases caused by viruses include the common cold and flu. Do you think viruses are prokaryotes or eukaryotes? The answer may surprise you. Viruses are not cells at all, so they are neither prokaryotes nor eukaryotes. Answer: viruses\n[EX A]: The common cold and flu are examples of human diseases caused by what tiny particles?\n\n[EX Q]: Passage: Plants are multicellular eukaryotes. They have organelles called chloroplasts and cell walls made of cellulose. Plants also have specialized reproductive organs. Almost all plants make food by photosynthesis. Life as we know it would not be possible without plants. Answer: photosynthesis\n[EX A]:" }, { "from": "gpt", "value": "How do most plants create food?\n\n" } ]
[ { "from": "human", "value": "Teacher:You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them.\nTeacher: Now, understand the problem? Solve this instance: Context Word: positive. \nQuestion: PersonX made a positive identification on PersonY for stealing a purse, so _ definitely saw the crime. \nAnswer: PersonX\nStudent:" }, { "from": "gpt", "value": "PersonX made a positive identification on PersonY for stealing a purse, so _ definitely did the crime." } ]
[ { "from": "human", "value": "In this task, you are given a dialogue from a conversation between an agent and a customer. Your task is to determine the speaker of the dialogue. Answer with \"agent\" or \"customer\".\n\nExample input: Hello. How may I aid you today?\nExample output: agent\nExample explanation: This is a pretty straightforward dialogue, and the speaker wants to help the other. So, the agent is the speaker.\nQ: I want to change my recent reservation due to some health issue.\nA:" }, { "from": "gpt", "value": "customer" } ]
[ { "from": "human", "value": "In this task, you're given two sentences, sentence 1 and sentence 2, and the genre they belong to. Your job is to determine if the two sentences belong to the same genre or not. Indicate your answer with Y and N respectively. Genres available include: face-to-face, government, letters, 9/11, slate, telephone, travel, verbatim, oup, fiction. Sentences belonging to 'face-to-face' genres relate to conversations or dialogues, 'government' encompasses information released from public government websites, 'letters' refers to any written work for philanthropic fundraising, '9/11' relates to information pertaining to the 9/11 attacks, 'oup' includes non-fiction works on the textile industry and child development, 'slate' refers to any cultural topic that appears in the slate magazine, 'telephone' includes telephonic dialogue, 'travel' deals with information in travel guides, 'verbatim' includes short posts regarding linguistics, and 'fiction' includes popular works of fiction like 'The Secret Adversary' etc.\n--------\nQuestion: Sentence 1: Among India's nature reserves, this is the best known because of Jim Corbett, the audacious hunter of the man-eating tigers of Kumaon. Sentence 2: The reserve is free from any animal. Genre: travel.\n\nAnswer: Y\n\n\nQuestion: Sentence 1: A major part of the pleasure of Darjeeling is in getting here. Sentence 2: The jousting competitions in Syte are not very well known outside of the region. Genre: travel.\n\nAnswer: N\n\n\nQuestion: Sentence 1: Young British Artists From the Saatchi Collection (Royal Academy of Art, London). Sentence 2: US industrial companies rely on Japanese techniques to function. Genre: slate.\n\nAnswer:" }, { "from": "gpt", "value": "N\n\n\n" } ]
[ { "from": "human", "value": "Given a sentence in English, provide an equivalent paraphrased version from the original that retains the same meaning.\n\n[Q]: The old high school became the Upper School , while the new building became lower school .\n[A]: The old grammar school became the Upper School while the new building became the Lower School .\n\n\n[Q]: Some Hebrew and Aramaic abbreviations may not be included here , and more can be found in the list of Aramaic abbreviations or in the list of Hebrew abbreviations .\n[A]: Some Hebrew and Aramaic abbreviations may not be included here , and more can be found in the list of Hebrew abbreviations or in the list of Aramaic abbreviations .\n\n\n[Q]: The conclusions are that we are all perfect spiritual ideas of the one divine Mind , and manifest Spirit , not a material body .\n[A]:" }, { "from": "gpt", "value": "The conclusions are that we are all perfect spiritual notions of one divine spirit and manifest the spirit , not a material body .\n\n\n" } ]
[ { "from": "human", "value": "Definition: In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to classify the command into one of these seven categories: (1) majority, (2) unique, (3) superlative, (4) count, (5) comparative, (6) aggregation, and (7) ordinal. \n Here are the defications of each category: \n 1. majority: Describing the majority values (most or all) over one column, with the scope of all table rows or a subset of rows \n 2. unique: Describing one unique row, regarding one column, with the scope of all table rows or a subset of rows \n 3. Superlative: Describing the maximum or minimum value in a column, with the scope of all table rows or a subset of rows \n 4. Ordinal: Describing the n-th maximum or minimum value in a column, with the scope of all table rows or a subset of rows \n 5. Comparative: Comparing two rows in the table, regarding their values in one column \n 6. Count: counting some rows in the table based on the values in one column, with the scope of all table rows or a subset of rows \n 7. Aggregation: Describing the sum or average value over a column, with the scope of all table rows or a subset of rows. \n Here are the definitions of logical operators for understanding of command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\nInput: eq { count { filter_eq { all_rows ; date ; 1 april 2006 } } ; 6 }\nOutput:" }, { "from": "gpt", "value": "count" } ]
[ { "from": "human", "value": "You will be given a piece of text either about an everyday event, or a general statement. If the event seems a plausible event to you, or the general statement makes sense matches your commonsense, output 'True', otherwise output 'False'.\nQ: It's easier for a person to drink a cup of water at once than to drink a gallon of water at once.\nA: " }, { "from": "gpt", "value": "True" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task you are given a sentence pair from wikipedia that have high lexical overlap. If the sentences have the same meaning and are just paraphrases of each other label them as \"Paraphrase\" , if not label them as \"Not paraphrase\". The two sentences are seperated by a new line.\n\nIn 1974 Cohen stood as the parliamentary candidate for the Liberal Party in Kensington North , and in 1979 he stood as its European candidate in London West .\nIn 1974 , Cohen was a parliamentary candidate for the Liberal Party in Kensington North , and in 1979 he stood as the European candidate in London West .\nOutput:" }, { "from": "gpt", "value": "Paraphrase" } ]
[ { "from": "human", "value": "Instructions: In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.\nInput: The workers at a refinery in a city that borders Staten Island belong to what specific chapter of their union ?\nOutput:" }, { "from": "gpt", "value": "Local No . 877" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you're given a pair of sentences, sentence 1 and sentence 2. Sentence 2 contradicts sentence 1. Your job is to alter sentence 2 so that the pair neither agree nor contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\nExample: Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had not been in the store.\nOutput: Tom had been shopping for fruit to give Jon.\nThe given sentence is a good alteration. If the changed sentence was something like: \"Tom had been sleeping in his house in that time\", it'd contradict the first sentence. But this given sentence neither agrees with the first sentence, nor contradicts it.\n\nNew input case for you: Sentence 1: Children play in a water fountain. Sentence 2: The kids are drowning.\nOutput:" }, { "from": "gpt", "value": "Kids are chasing each other around the fountain." } ]
[ { "from": "human", "value": "instruction:\nIn this task, you're given an article and an answer. Your task is to generate the fill-in-the-blank question for this answer based on the given article. The blanks are always at the end of the question, and can be filled with more than one word or phrase.\nquestion:\nArticle: Disposing of waste has been a problem since humans started producing it. As more and more people choose to live close together in cities,the waste disposal problem becomes increasingly difficult. During the eighteenth century,it was usual for several neighboring towns to get together to select a faraway spot as a dump site. People would transport household rubbish,rotted wood and old possessions to the site. Regularly some of the trash was burned and the rest was buried. The unpleasant sights and smells caused no problem because nobody lived close by. Factories and some other industrial sites also had waste to be disposed of. Those located on rivers often just poured the unwanted remains into the water. Others built huge burners with chimneys to deal with the problem. Several facts make these choices unacceptable to modern society. The first problem is space. Dumps , are most needed in heavily populated areas. Such areas rarely have empty land suitable. Farm areas are refusing to accept rubbish from elsewhere,cheap land in major city areas to dispose wastes is nonexistent . Awareness of pollution dangers has resulted in more strict rules of waste disposal. Pollution of rivers,ground water,land and air is a price people can no longer pay to get rid of waste. The amount of waste,however, continues to grow. Recycling efforts have become commonplace,and many towns require their people to take part. Even the most efficient recycling programs,however,can hope to deal with only about 50 percent of a city's reusable waste,so more people should be involved in recycling programs. \n Answer: Waste Disposal Problem\nanswer:\nThe most suitable title for this passage would be _ .\n\n\nquestion:\nArticle: \"Is it possible for Brownie not to be glad to be back after a happy stay at my uncle's?\"Miss Gauss asked Dad.\"It'll be all right. Give her a bit more to eat,\" he said in a low voice, without tearing his eyes from Brownie while his wife was busy packing Brownie's belongings, saying,\"Brownie is not so cute as her younger brother, Spotty. Take care of the little thing when walking him.\" It happened on the night of July 10th, 2013 before the Gausses took a trip to Hawaii. They entrusted their pet to me because they thought I was the first person they'd confide in. And another intention of theirs was that I had already trained Spotty into a wellknown pet in my community, which can act many tricks, such as \"Sit down!\" \"Stand up!\" \"Give me your right hand!\" \"Turn around!\" She can even sing, and, of course, that's just a strange sharp noise. Having seen them off, I took beautiful Brownie home in my arms, for fear that he would slip away. _ so I tried many ways to be his friend, which made Spotty rather unhappy. They often fought a battle, seemingly to break my roof loose. Soon, Brownie turned out to be an agreeable family member. He was an endearing pet, often begging for comforts in my arms. I seized the chance to train him and he achieved a lot, which I texted Mr.Gauss. They were so overjoyed and decided to fly home ahead of time to see Brownie's qualitative change. But,all this was thoroughly destroyed because of Brownie's death in a traffic accident. What a poor little creature!He was really dogged by bad luck, and he was saved from death shortly after his birth. For whatever reason,therefore, I was overwhelmed by feelings of guilt, which seemed to run most deeply in me. The best way to cheer ourselves up is to try first to cheer somebody else up. That will be an everlasting pain in my heart, a wound that does not heal. \n Answer: his owners would go on a trip\nanswer:\nBrownie went to the writer's home mainly because _ .\n\n\nquestion:\nArticle: The power of humor and laugher is numerous. They entertain us and make us feel good. But, above all, we have discovered that humor and laughter are the best medicine. They relieve pain, reduce stress and anxiety, and are anti-aging and longevity facilitators . They are extremely necessary for helping us to find and maintain a balance between life and work. However, they are slipping away from us. We have become far too serious. The only ones who still enjoy humor, laughter, fun and play to the fullest are young children. Children tend to laugh an average of 200 times a day. For adults, however, it is a totally different story. In the 1950s people laughed on average 18 times a day. Today, we are lucky if we average between 4-6 times a day. As a matter of fact, a recent study found that people laugh 6 more times in the presence of one person but 30 more times in a group of people. You can get a chuckle from jokes you get on the Internet, but it is not the same as belly jiggling laughter (a deep laugh) you get when you interact with others. Socializing with friends and relatives was much looked forward to. However, this is no longer the case. In fact, the majority of people can hardly find time, nor do they have the _ towards socializing outside home. They turn to electronic media such as television, computers, the Internet, videos, CDs, and audio equipment, which can provide them with instant self-entertainment at the push of a button. The workplace does not fare much better. Due to the pressures to produce more in the same or fewer hours available and to compete, for example, in a manufacturing field with cheaper labor elsewhere in the world, humor and laughter in the workplace have gradually eroded away. I have developed a real appreciation, perhaps closer to a strong desire for the power of humor and laughter. This encouraged me to write my first book titled \"The Power of Humor\" and subsequently my second book titled \"Kids Say the Goggonest Things\" based on the natural humor, laughter, play and fun that kids experience and they freely share with parents, grandparents and teachers. From writing about humor and laughter, people start to ask me to speak up for them. To date, I have developed a number of humor-laughter topics that I use in my keynote presentations. You are invited to subscribe to my free monthly e-magazine \"The Humormeister's Forum\" by clicking on the Free Humor E-zine navigation button on the website. \n Answer: humor of situations lies beneath\nanswer:\n" }, { "from": "gpt", "value": "According to the author, laughter is leaving us partly because _ .\n\n\n" } ]
[ { "from": "human", "value": "Q: Given a set of four words, generate the category that the words belong to. Words are separated by commas. The possible categories are social gathering, accomodation, physical property, measurement unit, corporate, nutritional value, boats, police punishment, location (proximity), card games, outdoor sport activity, military rank, baby animals, weather, consumer product, animals, boxing terminology, food, chocolate food, bird, type of sandwich, date status, body part, ocean, employment activity, moral characteristic, elements, poker, computers, construction, guitar part, shady activities, physical activity, kitchenware, temperature, type of rigidity, emotional status, season, mode of transportation, window material, activity, emotional display, geographical property, fried food, store status, widespread, aesthetic characteristic, alcoholic drinks, secretary duty, direction, personal characteristic, and animal.\nsunny, fair, deal, warm\nA:" }, { "from": "gpt", "value": "weather" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. Your answer should be chosen from the given text, and should not contain other words.\nQ: Victoria Santiago: Stay with me .\nVicky's older boyfriend: I 've got to go to work .\nVictoria Santiago: I 'll write you a note .\nVicky's older boyfriend: You have school .\nVictoria Santiago: You write me _ one _ .\nVicky's older boyfriend: I ca n't .\nVictoria Santiago: O - k ...\nVicky's older boyfriend: Maybe I can stay a while .\nA:" }, { "from": "gpt", "value": "note" } ]
[ { "from": "human", "value": "In this task, you are given a sentence from the research paper and your task is to classify the given sentence into the following categories: Background (Why is this problem important? What relevant works have been created before? What is still missing in the previous works? What are the high-level research questions? How might this help other research or researchers?), Purpose (What specific things do the researchers want to do? What specific knowledge do the researchers want to gain? What specific hypothesis do the researchers want to test?), Method (How did the researchers do the work or find what they sought? What are the procedures and steps of the research?), or Finding (What did the researchers find out? Did the proposed methods work? Did the thing behave as the researchers expected?). \n\nView is a key factor that influences property price." }, { "from": "gpt", "value": "background" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. The input is a tweet which can be classified as Hate Speech, Offensive or Normal. Given such a tweet, output the class the tweet belongs to. Hate Speech will contain threatening language towards the community targeted. Offensive language will contain abusive or discriminatory language towards the community targeted.\n\nhe said kike\n" }, { "from": "gpt", "value": "Hate Speech" } ]
[ { "from": "human", "value": "Instructions: In this task you will be given a list of dictionaries. A dictionary is a set of key-value pairs, where each key is unique and has a value associated with that key. You should sort the list of dictionaries from smallest to largest by their 'first' key. If there is two dictionaries with the same 'first' value then sort them by their 'second' key. Negative numbers should come before positive numbers.\nInput: [{'first': 65, 'second': -53}, {'first': 94, 'second': 98}]\nOutput:" }, { "from": "gpt", "value": "[{'first': 65, 'second': -53}, {'first': 94, 'second': 98}]" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task you are given a sentence. You must judge whether the object of the main clause is singular(like: apple) or plural(like: apartments). Label the instances as \"Singular\" or \"Plural\" based on your judgment.\nQ: She walked around the dragon and wrapped her arms as far around his neck as she could.\nA:" }, { "from": "gpt", "value": "Singular" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given inputs i, j, and A, where i and j are integers and A is a list. You need to find all elements of A from the ith element to the jth element, reverse the order in which they occur, and then concatenate them to output the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j. Perform the operations in order, i.e., do not concatenate the elements and then reverse the string.\n\n2, 12, ['O', 't', 'm', '2755', 'S', 'W', 'l', '2659', '7923', '6023', 'X', '8997', 'L', '5529', 'w', 'U', 'B', 'L', '8811', 'e', '1035', 'T', '8781', 'Q']\n" }, { "from": "gpt", "value": "8997X602379232659lWS2755mt" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a sentence or phrase in English. You must translate it to Xhosa in a way that is equivalent in terms of meaning and grammatically correct.\nQ: The lazy painter of a boat is then secured to this.\nA:" }, { "from": "gpt", "value": "Enobuvila yokuzoba izikhephe nayo yayikhuselwe kule." } ]
[ { "from": "human", "value": "Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.\n\nExample Input: walk left twice and jump around right thrice\nExample Output: I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP\n\nExample Input: walk twice after jump around right thrice\nExample Output: I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_WALK I_WALK\n\nExample Input: jump around left and walk around right thrice\nExample Output:" }, { "from": "gpt", "value": "I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK\n\n" } ]
[ { "from": "human", "value": "Q: In this task, you are given a question and a context passage. You have to answer the question based on the given passage.\nWho owns the only railways in Israel?, Context: Israel has 18,096 kilometers (11,244 mi) of paved roads, and 2.4 million motor vehicles. The number of motor vehicles per 1,000 persons was 324, relatively low with respect to developed countries. Israel has 5,715 buses on scheduled routes, operated by several carriers, the largest of which is Egged, serving most of the country. Railways stretch across 949 kilometers (590 mi) and are operated solely by government-owned Israel Railways (All figures are for 2008). Following major investments beginning in the early to mid-1990s, the number of train passengers per year has grown from 2.5 million in 1990, to 35 million in 2008; railways are also used to transport 6.8 million tons of cargo, per year.\nA:" }, { "from": "gpt", "value": "government" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, positions of two consecutive words have been swapped. You need to output the position of the swaped words. e.g. in the sentence 'Seattle has nice a weather', the word 'a' and 'nice' have been swapped. These words are at 3rd and 4th position respectively. So, the output should be (3, 4). Note that the index of first word is 1.\nProblem:A person on a snow in board the air\nSolution:" }, { "from": "gpt", "value": "(6, 7)" } ]
[ { "from": "human", "value": "In this task, you will be shown a conversation. You need to write a question with three choices for the conversation. Your question should be answerable based on the conversation and only have one correct answer. Note that you don't need to answer your question. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\nExample: W: The movie next Tuesday has been cancelled due to lack of interest. M: What do you mean? W: Well, by last night only a few tickets has been sold.\nExample solution: What can we conclude about the movie? (A) They want to buy the tickets for the movie. (B) The tickets for the movie were sold. (C) The movie will not be shown.\nExample explanation: This is a good example. Based on the conversation, the movie has been canceled, and it will not be shown. We could understand that only option (C) is correct. As mentioned in the conversation, only a few tickets have been sold, so option (B) is incorrect. We don't know if they wanted to buy a ticket or not, so option (A) is incorrect as well.\n\nProblem: M: Do we have to get the opera tickets in advance? W: Certainly. Tickets at the door are usually sold at a higher price.\n" }, { "from": "gpt", "value": "Solution: What does the woman imply? (A) It's better to buy the tickets beforehand. (B) The tickets are sold in advance at half price. (C) It's difficult to buy the tickets on the spot." } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. You are given an original reference as well as a system reference. Your task is to judge the quality of the system reference. If the utterance is grammatically correct and fluent output 1, else output 0.\n\nSystem Reference: may i ask near where?\nOriginal Reference: where would you like the hotel to be near to?.\n" }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "Given a scientific question, generate a correct answer to it.\n\n[Q]: Strong, stable bonds between carbon atoms produce complex molecules containing chains, branches, and rings; the chemistry of these compounds is called what?\n[A]: organic chemistry\n\n\n[Q]: Vertebrates. from the smallest of fish to us. one of the main features we all have in common is our what?\n[A]: backbone\n\n\n[Q]: Fractures, osteoarthritis, and rickets are problems of which body system?\n[A]:" }, { "from": "gpt", "value": "skeletal system\n\n\n" } ]
[ { "from": "human", "value": "Q: In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty.\nPassage: Italian Premier Romano Prodi, who narrowly beat former premier Silvio Berlusconi in April's general election, has been struggling to gain support among some of its allies for the budget, which is aimed at promoting growth and bringing the Italian deficit to within 3 percent of GDP by next year to meet Rome's EU commitments. Question: What is hoped to happen after Prodi beat Berlusconi? Events: ['beat', 'struggling', 'aimed', 'promoting', 'growth', 'meet', 'commitments']\nA:" }, { "from": "gpt", "value": "growth" } ]
[ { "from": "human", "value": "In this task you are given a premise and two alternatives in Indonesian. You must choose the alternative that is more plausibly the cause or effect of the situation described by the premise. The input format is \"premise\n(1)alternative_1(2)alternative_2\", the output should either be \"1\" or \"2\" based on your judgment.\n\nEx Input:\nGadis itu menghafalkan kodenya.\n(1)Dia membacakannya ke dirinya sendiri.(2)Ia lupa mencatatnya.\n\nEx Output:\n1\n\n\nEx Input:\nBocah itu menendang mesin penjual otomatis itu.\n(1)Banyak kembalian keluar dari mesin itu.(2)Kantung keripik yang ia beli itu macet di dalam mesin.\n\nEx Output:\n2\n\n\nEx Input:\nPria itu menandatangani petisi para aktivis.\n(1)Dia mendukung perjuangan mereka.(2)Dia mencela mereka karena dikira orang gila.\n\nEx Output:\n" }, { "from": "gpt", "value": "1\n\n\n" } ]
[ { "from": "human", "value": "Definition: In this task, you are given inputs i, j, and A, where i and j are integers and A is a list. You need to find all elements of A from the ith element to the jth element, reverse the order in which they occur, and then concatenate them to output the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j. Perform the operations in order, i.e., do not concatenate the elements and then reverse the string.\nInput: 4, 13, ['1257', '7579', '1783', 'M', 'Z', '9093', '5889', 'T', '5301', '3725', 'O', '3127', 'w', '4763', 'N', 'C', '4135', 'l', '2885', 'c', 'B', 'e']\nOutput:" }, { "from": "gpt", "value": "w3127O37255301T58899093ZM" } ]
[ { "from": "human", "value": "You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. You are required to assign a label 'formal' if there is an absence of emotion and a presence of questions anywhere within the conversation. If such pattern is not found assign the label 'informal'.\n\n[EX Q]: Person1: I never understand why these shops have so much liquor . \n Person2:What do you mean ? It's because it's much cheaper to buy liquor duty-free . \n Person1: But why ? Why don't people like to buy shirts duty-free ? Or shoes ? I just don't understand why it's always liquor . \n Person2:Well , it's because in most countries liquor has a higher tax on it . \n Person1: You mean liquor has a higher tax than other things ? \n Person2:Yes , of course . Didn't you know that ? \n Person1: No , I didn't . How high is the tax ? \n Person2:Well , it is different in different countries.But it's because of the high tax that buying liquor duty-free is such a good deal . \n Person1: Why would the government want to tax liquor so much ? \n Person2:Liquor is considered a luxury item.And also , it is considered as something that isn't very healthy.So if people want to buy it , the government thinks it has the right to tax it . \n Person1: That's why a lot of people buy cigarettes here too , isn't it ? \n Person2:Of course . Cigarettes are also taxed very heavily . \n[EX A]: formal\n\n[EX Q]: Person1: Amy , could you help me with this work ? \n Person2:Sorry , I'm busy . Why don't you ask Alice ? \n Person1: Okay . \n[EX A]: informal\n\n[EX Q]: Person1: Good morning , Sir . \n Person2:Hello . I'm here today to pay in some foreign currency . Is that possible at this counter ? \n Person1: Of course , Sir . What kind of currency would you like to deposit ? And what is the amount you would like to pay in ? \n Person2:10,000 Japanese yen . \n Person1: OK , Sir . Would that be Fixed or Current Deposit ? \n Person2:Fixed . \n Person1: And how long are you depositing for ? \n Person2:For one year , that's what I usually do . Better interest , you know . \n[EX A]:" }, { "from": "gpt", "value": "formal\n\n" } ]
[ { "from": "human", "value": "Teacher:You will be given a person's personality, and a history of a conversation this person has had. You will be given four candidate sentences to complete the conversation, based on the context. Choose one and answer with the text.\nTeacher: Now, understand the problem? Solve this instance: Personality: I like to use candles instead of lights.\nI love photography.\nI enjoy spending a lot of money on my hobbies.\nI do not like waking up early.\nI love the sound of the rain.\nChat history: -Hi how are you doing.\nCandidates 1) How are you today. 2) Hey I am doing ok. Did they just die? 3) Cool. What do you like to do? 4) Righto. I work at a flower shop. I usually spend my breaks reading used books.\nStudent:" }, { "from": "gpt", "value": "How are you today." } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given an input stream, and your task is to produce a grammatically correct version of the input sentence. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a grammatically correct version of the input stream. Stream words are in [] and have been separated with a comma. The sentence can contain words that have case, punctuation, stem-based, intra-word, and digit punctuation errors that need to be corrected. For example, the text should be uppercased/lowercased as per necessity (like the beginning of a sentence, proper nouns, etc.), and digits need to be normalized (6 as six and so on). Note that you don't need to normalize the years. You don't need to fully edit the sentences, if end of the input stream contains sentence fragments, keep them as is.\nProblem:['I', 'always', 'loved', 'writing', 'and', 'telling', 'stories', 'but', 'specifically', 'having', 'like', 'a', 'pen', 'or', 'a', 'crayon', 'in', 'my', 'hand', 'and', 'a', 'piece', 'of', 'paper', 'in', 'front', 'of', 'me', 'and', \"it's\", 'always', 'something', 'I', 'just', 'really', 'enjoyed', 'my', 'parents', 'have', 'stories', 'about', 'finding', 'me', 'when', 'I', 'was', 'like', 'two', 'or', 'three', 'marking', 'up', 'notebooks', 'that', 'they', 'had', 'but', 'not', 'like', 'drawing', 'on', 'the', 'marking', 'in', 'the', 'lines', 'I', \"couldn't\", 'write', 'yet', 'but', \"it's\", 'like', 'oh', 'yeah', 'I', 'just', 'want', 'to', 'get', 'these', 'things', 'these', 'squiggles', 'after', 'the', 'other', 'squiggles', 'in', 'the', 'lines', 'and', 'when', 'I', 'started', 'going', 'to', 'grade', 'school', 'writing']\nSolution:" }, { "from": "gpt", "value": "['I', 'always', 'loved', 'writing', 'and', 'telling', 'stories,', 'but', 'specifically', 'having', 'like', 'a', 'pen', 'or', 'a', 'crayon', 'in', 'my', 'hand', 'and', 'a', 'piece', 'of', 'paper', 'in', 'front', 'of', 'me,', 'it', 'was', 'always', 'something', 'I', 'just', 'really', 'enjoyed.', 'My', 'parents', 'have', 'stories', 'about', 'finding', 'me', 'when', 'I', 'was', 'like', 'two', 'or', 'three', 'marking', 'up', 'notebooks', 'that', 'they', 'had,', 'but', 'not', 'like', 'drawing', 'on', 'them,', 'marking', 'in', 'the', 'lines.', 'I', \"couldn't\", 'write', 'yet,', 'but', \"it's\", 'like', 'okay', 'yeah', 'I', 'just', 'want', 'to', 'get', 'these', 'things,', 'these', 'squiggles', 'after', 'the', 'other', 'squiggles', 'in', 'the', 'lines.', 'And', 'when', 'I', 'started', 'going', 'to', 'grade', 'school,', 'writing']" } ]
[ { "from": "human", "value": "Instructions: In this task, you are given a review of a movie and a boolean question whether this review has positive sentiment or negative sentiment. Your task is to generate answer \"yes\" when the tweet has that particular sentiment, otherwise generate answer \"no\".\nInput: Review: The final film for Ernst Lubitsch, completed by Otto Preminger after Lubitsch's untimely death during production, is a juggling act of sophistication and silliness, romance and music, fantasy and costume dramatics. In a 19th century castle in Southeastern Europe, a Countess falls for her sworn enemy, the leader of the Hungarian revolt; she's aided by her ancestor, whose painted image magically comes to life. Betty Grable, in a long blonde wig adorned with flowers, has never been more beautiful, and her songs are very pleasant. Unfortunately, this script (by Samson Raphaelson, taken from an operetta by Rudolf Schanzer and E. Welisch) is awash with different ideas that fail to mesh--or entertain. The results are good-looking, but unabsorbing. 1/2 from *** Question: is it a positive review?\nOutput:" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given an abstract of article. Your task is to generate title for this article. Preferred titles are under thirty words.\nExample: Alterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.\nOutput: Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.\nThis title is appropriate for the given abstract because the focus of this abstract is cerebral white matter assesment.\n\nNew input case for you: Late Embryogenesis Abundant Proteins (LEAPs) are ubiquitous proteins expected to play major roles in desiccation tolerance. Little is known about their structure - function relationships because of the scarcity of 3-D structures for LEAPs. The previous building of LEAPdb, a database dedicated to LEAPs from plants and other organisms, led to the classification of 710 LEAPs into 12 non-overlapping classes with distinct properties. Using this resource, numerous physico-chemical properties of LEAPs and amino acid usage by LEAPs have been computed and statistically analyzed, revealing distinctive features for each class. This unprecedented analysis allowed a rigorous characterization of the 12 LEAP classes, which differed also in multiple structural and physico-chemical features. Although most LEAPs can be predicted as intrinsically disordered proteins, the analysis indicates that LEAP class 7 (PF03168) and probably LEAP class 11 (PF04927) are natively folded proteins. This study thus provides a detailed description of the structural properties of this protein family opening the path toward further LEAP structure - function analysis. Finally, since each LEAP class can be clearly characterized by a unique set of physico-chemical properties, this will allow development of software to predict proteins as LEAPs.\nOutput:" }, { "from": "gpt", "value": "Computational and Statistical Analyses of Amino Acid Usage and Physico-Chemical Properties of the Twelve Late Embryogenesis Abundant Protein Classes" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you're given a context, a sentence, and a character. The sentence describes an action or job of the given character. Also, the context provides more information about the sentence or the character. Your task is to return one of the emotions which are expressed by the Character in the given sentence. For that you can use the Context; however, Context is not provided in all the inputs. Also, in some inputs, there can be zero emotion; for that return 'None'.\nPart 2. Example\nContext: A cook was carrying an armful of oranged in the kitchen. \n Sentence: He dropped one on the floor by accident. \n Character: Cook\nAnswer: annoyed\nExplanation: The cook dropped one orange on the floor, so, he must feel annoyed at that time.\nPart 3. Exercise\nContext: None \n Sentence: June fell out of her tree house. \n Character: Her mom\nAnswer:" }, { "from": "gpt", "value": "None" } ]
[ { "from": "human", "value": "Teacher: Given an abstract, indicate which of the provided candidate titles (Option1 and Option2) best describes it (respond with the text of the title, not option1/2).\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nAbstract: Some patients converted from ventricular fibrillation to organized rhythms by defibrillation-trained ambulance technicians (EMT-Ds) will refibrillate before hospital arrival. The authors analyzed 271 cases of ventricular fibrillation managed by EMT-Ds working without paramedic back-up. Of 111 patients initially converted to organized rhythms, 19 (17%) refibrillated, 11 (58%) of whom were reconverted to perfusing rhythms, including nine of 11 (82%) who had spontaneous pulses prior to refibrillation. Among patients initially converted to organized rhythms, hospital admission rates were lower for patients who refibrillated than for patients who did not(53% versus 76%, P = NS), although discharge rates were virtually identical (37% and 35%, respectively). Scene-to-hospital transport times were not predictively associated with either the frequency of refibrillation or patient outcome. Defibrillation-trained EMTs can effectively manage refibrillation with additional shocks and are not at a significant disadvantage when paramedic back-up is not available. \n Which is the apt title for the abstract? option1: Refibrillation managed by EMT-Ds option2: Maintenance of compliance in a small diameter arterial prosthesis.\nSolution: Refibrillation managed by EMT-Ds\nReason: The abstract is about refibrillation and it is also mentioned in the abstract that it is managed by EMT-Ds. So it is an apt title.\n\nNow, solve this instance: Abstract: In recent years it has become increasingly apparent that cough is frequently the sign of airway hyperreactivity. While the association between cough and wheezing is well recognized in asthmatics, cough may be the only clinical manifestation of this problem. Emergency physicians frequently have occasion to evaluate the coughing patient. Awareness of this clinical entity should facilitate appropriate evaluation, management, and referral of these patients. \n Which is the apt title for the abstract? option1: Cough variant asthma [published erratum appears in Pediatr Emerg Care 1987 Mar;3(1):9] option2: Prediction and evaluation of brainstem function by auditory brainstem responses in patients with uncal herniation.\nStudent:" }, { "from": "gpt", "value": "Cough variant asthma [published erratum appears in Pediatr Emerg Care 1987 Mar;3(1):9]" } ]
[ { "from": "human", "value": "In this task, you're given a review from Amazon and your task is to generate the name of the category of the product based on the review given by the user. The categories are: kitchen, office product, watch, wireless, other, toy, digital video download, camera, jewelry, pet products, sports, industrial supplies, baby product, grocery, drugstore, home improvement, pc, shoes, automotive, digital ebook purchase, musical instruments, beauty, book, electronics, lawn and garden, apparel, home, video games, luggage, furniture, personal care appliances.\nExample: Arrived broken. Manufacturer defect. Two of the legs of the base were not completely formed, so there was no way to insert the casters. I unpackaged the entire chair and hardware before noticing this. So, I'll spend twice the amount of time boxing up the whole useless thing and send it back with a 1-star review of part of a chair I never got to sit in. I will go so far as to include a picture of what their injection molding and quality assurance process missed though. I will be hesitant to buy again. It makes me wonder if there aren't missing structures and supports that don't impede the assembly process.\nExample solution: furniture\nExample explanation: The customer gives a review of the product which belongs to the furniture category because we can see it from the way the customer describes his experience sharing how he unpackaged his chair.\n\nProblem: I had to order this product twice. The first order was delivered with one end opened with no LEGO pieces in the plastic bags. Legos were falling out of the box. Promptly returned it and reordered. The second order was received today. At least the pieces were in sealed bags within the box, but the box was still opened on one end because it had two strips of scotch tape holding it down.\n" }, { "from": "gpt", "value": "Solution: toy" } ]
[ { "from": "human", "value": "In this task you will be given a text passage from a trivia quiz. You should choose the category this question belongs to from these categories: History, Science, Social Science, Fine Arts, Literature. You can only choose one category, so if in doubt, please choose the closest match.\n\nThe central figure in this work is possibly based on Simonetta Vespucci. The bottom-left corner of this work displays cattails, while the right side of this painting contains three tall trees and an orange grove in the background, as well as a red-haired figure who extends a red, floral-patterned robe towards the title figure. On the left side of this painting, many roses fall around Chloris and Zephyr, who blow wind towards the title figure as she stands upon a clamshell and emerges from the sea. For 10 points, name this Botticelli painting which depicts the title Roman goddess of love." }, { "from": "gpt", "value": "Fine Arts" } ]
[ { "from": "human", "value": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the count of all the numerical elements in the given list. Return 0 if no numerical element in the list.\nExample: ['238', 'h', '92', 'U', '2799']\nExample solution: 3\nExample explanation: Here, the numbers in the input list are '238', '92' and '2799', hence their count is 3.\n\nProblem: ['a', 'I', 'J', 'Z', 'P', '5821', '7435', '299', '1715', 'M', 'O', 'z', 'n', 'f', '9437', '3073', 'D', 'C', 'n', '5231', 'h', '535', '8035', 'M', 'i', 'I', 'z', 'w', '2643', '7083', '8471', '2135', '655', '1935', 'i', '5439', '7991']\n" }, { "from": "gpt", "value": "Solution: 17" } ]
[ { "from": "human", "value": "Detailed Instructions: Classify the given a piece of financial news into three classes: positive, negative, and neutral. Output must be 'positive', 'negative', or 'neutral'.\nQ: The company plans to expand into the international market through its subsidiaries and distributors from 2011 onwards .\nA:" }, { "from": "gpt", "value": "positive" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you will be given a list. The list is several integers and letters separated with a comma, written within a []. You can create new lists by dropping one of the items in the input list. Your task is to write a list containing all the possible lists you can make by dropping one item from the input list. For example, if the input list contains two items, you can drop one of the items each time. So the output should be a list comprising two inner lists that you have created by decreasing the items.\nProblem:['9', '9', 'z', '2']\nSolution:" }, { "from": "gpt", "value": "[['9', '9', 'z'], ['9', '9', '2'], ['9', 'z', '2'], ['9', 'z', '2']]" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given two statements. The task is to output whether a given textual premise, i.e. Statement 2, entails or implies a given scientific fact, i.e. Statement 1. The output should be 'entails' if Statement 2 supports Statement 1 and should be 'neutral' otherwise.\nSee one example below:\nProblem: Sentence 1: The sum of all chemical reactions that take place within an organism is known as metabolism. Sentence 2: Metabolism is the sum total of all chemical reactions performed by an organism.\nSolution: entails\nExplanation: Sentence 2 gives out supporting information about the Metabolism hence it is correct\n\nProblem: Sentence 1: The theory of biological evolution do transitional fossils best support. Sentence 2: This theory is not supported by fossil evidence.\nSolution:" }, { "from": "gpt", "value": "neutral" } ]
[ { "from": "human", "value": "In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write the required POS tag answering the question. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb\n\n[EX Q]: What is the part-of-speech tag of the word \"position\" in the following question: Which position had a player score 9 goals between 2004 and 2011 and moved from a club that had only student members back in 1905 ?\n[EX A]: NN\n\n[EX Q]: What is the part-of-speech tag of the word \"that\" in the following question: What player was drafted into the 1967 NFL/AFL league as the position that makes field goals and extra points , after he played for a college team that played its games in the Clifford B . & Audrey Jones Stadium ?\n[EX A]: WDT\n\n[EX Q]: What is the part-of-speech tag of the word \"sites\" in the following question: In what season does the Historic Site that was added to the list of historic sites in the first month of the year used by recreational travelers and visitors ?\n[EX A]:" }, { "from": "gpt", "value": "NNS\n\n" } ]
[ { "from": "human", "value": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A after the first i elements. i will always have a value less than the length of A.\n\nInput: Consider Input: 10, ['l', '3143', 'q', '3951', 'j', 'b', '8375', '7543', '7561', '7159', '6405', 'r', '3897', '849', 'Q', 'p', '9481', 'Y', 'O', '2329', '6915', '977', 'V', '9533', '9149', 'H', 'Y', 't', 'Y', 'y']\n\nOutput: 6405, r, 3897, 849, Q, p, 9481, Y, O, 2329, 6915, 977, V, 9533, 9149, H, Y, t, Y, y\n\n\nInput: Consider Input: 1, ['G', '8193', 'r', 'h', '8677']\n\nOutput: 8193, r, h, 8677\n\n\nInput: Consider Input: 3, ['d', 'I', 'B', '3665', '1187', 'O', '5685', 'a', '6407', '9187', 'Y', 'S', 'Y', 'S', '1731', 'w', 'Z', 'n', '6509', '4225', 'w', '3785', '4043', '8243', '8287', '7633', 'd', '2793', '6015', 't']\n\n" }, { "from": "gpt", "value": "Output: 3665, 1187, O, 5685, a, 6407, 9187, Y, S, Y, S, 1731, w, Z, n, 6509, 4225, w, 3785, 4043, 8243, 8287, 7633, d, 2793, 6015, t\n\n\n" } ]
[ { "from": "human", "value": "You are given a science question (hard-level) and four answer options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer based on scientific facts, knowledge, and reasoning. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D'. There is only one correct answer for each question.\n\nQ: Which will most likely result from a low-pressure weather system? \n (A) warm temperatures (B) cloudy conditions (C) clear conditions (D) cool temperatures\n\nA: B\n**\nQ: Some bacteria use iron found in their systems as a means to guide their movement. Which stimulus most likely triggers this movement mechanism? \n (A) magnetism (B) oxygen (C) light (D) heat\n\nA: A\n\nQ: Since Earth radiates heat into outer space, why is Earth's surface not becoming colder? \n (A) Earth constantly takes in more heat from the Sun. (B) Earth has forests that provide heat through photosynthesis. (C) Earth has oceans that store heat. (D) Earth absorbs extra heat from molten lava.\n\nA:" }, { "from": "gpt", "value": "A\n**\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. The task is to write a full sentence or two using all of the information given. The sentence(s) will be a brief review of a restaurant. Use all of the information provided.\n\nname[xname], eattype[restaurant], cuisine[Japanese], rating[3 out of 5]\n" }, { "from": "gpt", "value": "xname is a Japanese restaurant rated 3 out of 5 by customers" } ]
[ { "from": "human", "value": "You're given a sentence and your task is to classify whether the sentence is acceptable or not. Any sentence which is grammatically correct, has a naturalistic text, is written by a native speaker and which minimizes superfluous content is acceptable, otherwise unacceptable. If the sentence is acceptable then write \"acceptable\", otherwise \"unacceptable\".\n\nHarriet alternated folk songs with pop songs." }, { "from": "gpt", "value": "acceptable" } ]
[ { "from": "human", "value": "You are given a password and you need to generate the number of steps required to convert the given password to a strong password. A password is considered strong if (a) it has at least 6 characters and at most 20 characters; (b) it contains at least one lowercase letter and one uppercase letter, and at least one digit; (c) it does not contain three repeating characters in a row. In one step you can: (1) Insert one character to password, (2) delete one character from password, or (3) replace one character of password with another character.\nQ: password = D2EhsTBAY5DVgrgZ3\nA: " }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a sentence in Italian, generate a new Italian sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\nProblem:E' probabile che troviate un container in un porto.\nSolution:" }, { "from": "gpt", "value": "E' probabile che troviate un contenitore in una miniera." } ]
[ { "from": "human", "value": "Detailed Instructions: Given a scientific passage and an answer, generate a question for the given answer.\nProblem:Passage: The deprotonated form of an acid is referred to as its conjugate base. Similarly, the protonated form of a base is referred to as its conjugate acid. Answer: becomes more basic\nSolution:" }, { "from": "gpt", "value": "As ph increases what happens to a solution?" } ]
[ { "from": "human", "value": "You are given an original reference as well as a system reference. Your task is to judge the informativeness of the system reference. If the utterance provides all the useful information from the meaning representation output 1, else output 0.\n\nSystem Reference: red door cafe, is good for brunch.\nOriginal Reference: red door cafe is good for brunch.\n1\n\nSystem Reference: x is a restaurant in x, near to x and x in the moderate price range.\nOriginal Reference: x is an inexpensive restaurant located close to x and close to x in the x locality.\n1\n\nSystem Reference: he harbor court hotel c a kimpton hotel is located near soma.\nOriginal Reference: harbor court hotel c a kimpton hotel which is near soma.\n" }, { "from": "gpt", "value": "0\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you will be presented with a passage, and you need to write an implausible answer to to fill in the place of \"_\". Your answer should be incorrect, but should not be out of context. Try using words that are related to the context of the passage, but are not the correct answer. Even though there exist multiple wrong answers, we only need a single wrong answer.\nProblem:(CNN) For the past two decades, Harvard, the nation's oldest and arguably most prestigious institution of higher learning, has been a primary front in the assault on Affirmative Action. Since the early 1990s, it has been subject to a nearly continuous series of lawsuits and administrative complaints alleging that its admissions practices, which embrace \"holistic\" standards of admission that look beyond test scores and grades to take character and cultural context into account, are discriminatory against Asian applicants, whose test scores and grades are on average higher than other applicants. The complaints quietly add that these standards are also discriminatory against whites, who currently make up 52.8% of admittances. Asians make up another 21.1%.Jeff Yang: A new proposal to make Harvard tuition free is really a tactic to take down Affirmative ActionThe primary beneficiaries of a free Harvard are wealthy applicants whose families can afford to pay \n Question:The free-tuition initiative is ultimately a bait and switch: Upon election, they intend to demand \"transparency\" in Harvard's admissions process, specifically arguing for the release of data intended to expose what they believe to be persistent anti-_ (and anti-white) bias.\nSolution:" }, { "from": "gpt", "value": "Harvard" } ]

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.