Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "from": "human", "value": "Definition: In this task, you are given a text from tweets and a boolean question whether this tweet 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: Tweet: [Link] - me and my sis @ Piccadilly Circus Question: is it a negative tweet?\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 inputs i and A, where i is an integer and A is a list. You need to list all the elements of A preceding the last i elements. i will always have a value less than the length of A.\nExample: 3, ['a', '34', 'f', '931', '7', '3432', '13245', '762']\nOutput: a, 34, f, 931, 7\nHere, all the elements except the last 3 from the list are 'a', '34', 'f', '931', and '7'.\n\nNew input case for you: 6, ['u', '8889', 'Z', 'L', 'B', '5763', '9893', '3181', '9975', '4645', '2233', '281']\nOutput:" }, { "from": "gpt", "value": "u, 8889, Z, L, B, 5763" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task you will be given a list of integers. You should remove any integer that is not prime. A prime integer is an integer that is only divisible by '1' and itself. The output should be the list of prime numbers in the input list. If there are no primes in the input list an empty list (\"[]\") should be returned.\n\n[927, 599, 139, 691, 773, 757, 306, 677, 128, 326, 977, 433, 421, 311, 606, 2, 197, 263, 980, 760]\n" }, { "from": "gpt", "value": "[599, 139, 691, 773, 757, 677, 977, 433, 421, 311, 2, 197, 263]" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task you will be given a list of integers. For every element in the list, if the element is even you should divide by two, if the element is odd you should multiply by three then add one. The output should be a list of integers that is the result of applying that logic to the input list.\nQ: [29, 70, 108, 147]\nA:" }, { "from": "gpt", "value": "[88, 35, 54, 442]" } ]
[ { "from": "human", "value": "Instructions: Given a scientific question, generate an incorrect answer to the given question. The incorrect answer should be a plausible alternative to the correct answer. The answer should be some other item belonging to the same category as the correct answer but should be incorrect.\nInput: What are the two components of the ecf?\nOutput:" }, { "from": "gpt", "value": "proteins and if" } ]
[ { "from": "human", "value": "Teacher:In this task, a passage will be given and the goal is to identify an event from the passage. An event is defined as a single word representing something that happened, is happening, or may happen. An event can be factual or hypothetical, positive or negative, certain or uncertain. While most events are based on verbs, an event can also be based on a noun (ex. storm, snow, rainfall) or a copula verb (is, was, been, etc.). The event must not be a pronoun or an adjective. For noun events with multiple words, use the last word in the phrase as event.\nTeacher: Now, understand the problem? Solve this instance: Passage: Cuban exiles in Miami will now ``proceed with all their resources to impede or delay'' the ruling, Cuba predicted Wednesday. ``We cannot stop mobilizing!\nStudent:" }, { "from": "gpt", "value": "proceed" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story; note that the selected choices may fit into the story at any point. Indicate your selected choices in order, i.e., as 'ab'/'bc'/'ac' and not as 'ba'/'ca'/'cb'. If options are equally plausible, pick the ones that make more sense.\nExample: Title: Marcus Buys Khakis. Marcus needed clothing for a business casual event. He decided to buy a pair of khakis. The pair he bought fit him perfectly. Choices: a. Marcus was happy to have the right clothes for the event. b. He left in a huff for having his ideas mocked. c. All of his clothes were either too formal or too casual.\nOutput: ac\nMarcus is buying clothes for a business event and not presenting an idea.\n\nNew input case for you: Title: I put my dog in training school. He can now sit and stand. He will be finished in 3 weeks. Choices: a. They are very good teachers. b. He is learning a lot of new tricks. c. Jim wound up losing several pounds.\nOutput:" }, { "from": "gpt", "value": "ab" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\nQ: Beginning: I sent flowers and a big cookie to my wife for V Day. Middle: My wife enjoyed the gift. Ending: I was glad to show my love.\nA:" }, { "from": "gpt", "value": "My husband enjoyed the gift." } ]
[ { "from": "human", "value": "In this task you will be given a list of integers. For every element in the list, if the element is positive you should multiply it by 2. If the element is negative you should multiply it by -3. The output should be a list of integers that is the result of applying that logic to the input list.\n Note: A list is presented with comma separated numbers inside two brackets.\nOne example is below.\nQ: [-7, -1, 8, 7, -8]\nA: [21, 3, 16, 14, 24]\nRationale: Every negative number is multiplied by -3 and every positive number is multiplied by 2. So this is a good example.\nQ: [36, 2, -74, 6, -17, -80, 52, -8, -12, -44]\nA:" }, { "from": "gpt", "value": "[72, 4, 222, 12, 51, 240, 104, 24, 36, 132]" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a word. You should respond with a valid sentence which contains the given word. Make sure that the sentence is grammatically correct. You may use the word in a different tense than is given. For example, you may use the word 'ended' in the output where the given input word is 'end'.\nProblem:remission\nSolution:" }, { "from": "gpt", "value": "Her cancer was in remission." } ]
[ { "from": "human", "value": "Q: Given an Amazon customer review, write a title for the review. The preferred titles are under fifteen words.\nThe product works as advertised. This is an excellent solution for what I needed. I wanted to be able to watch cable TV in a bedroom with no cable connection available. The adjacent bedroom has a cable connection / cable digital box. I am able to watch the cable TV in the bedroom with the box thanks to the pass through HDMI connection on the IOGEAR transmitter. I am also able to watch cable TV in the 2nd bedroom too with the IOGEAR receiver. The quality of the video and audio is GREAT. I am 100% satisfied with the IOGEAR wireless digital kit. The distance between the transmitter and receiver is about 30 feet with one wall (drywall and wood studs) in between. I highly recommend this product.\nA:" }, { "from": "gpt", "value": "Awesome product for streaming a TV signal - video and audio excellent!" } ]
[ { "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.\nYou 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: there is a chinese restaurant on x called x.\nOriginal Reference: x is a chinese restaurant in x.\nSolution: 1\nWhy? The system reference is grammatically correct and fluent.\n\nNew input: System Reference: you may find the noe 7s nest bed and breakfast at 1257 guerrero st.\nOriginal Reference: the address is 1257 guerrero st for noe 7s nest bed and breakfast.\nSolution:" }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task you will be given some text dialogue and you need to infer the underlying emotion of the text. The possible emotions are happy, sad, angry, or other.\n\nyou are not smart but still and i'm not polite you look like stupid\nOutput:" }, { "from": "gpt", "value": "angry" } ]
[ { "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 position of all the alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.\nInput: ['a', 'C', 'p', 'E', 'Q', 'x', '8013', '9851', 'c', 'y', 'O']\nOutput:" }, { "from": "gpt", "value": "1, 2, 3, 4, 5, 6, 9, 10, 11" } ]
[ { "from": "human", "value": "Q: This task involves creating questions from a given passage that involve some kind of complex reasoning (including numerical reasoning). \nThe generated questions must require looking at more than one part of the passage to answer. Try to use a variety of reasoning types in your questions (some of the sample reasoning types are illustrated in the 'positive examples' field) and also have a variety of answer types (spans, numbers, dates). A span is a continuous phrase taken directly from the passage or question. In such questions, the answer spans are recommended to be five words. Questions with answer type \"number\", are expected to start with \"How many\". For instance, \"How long did an event last?\" can be phrased as \"How many years did an event last?\". To increase diversity, try to create more questions for which the answer will be multiple spans. Please create questions that require AT LEAST 2 arithmetic operations as illustrated in the 'positive examples' field. You are encouraged to try DIFFERENT COMBINATIONS of operations and not just limit to the combinations shown in those examples. The more challenging questions you create, the better it is.\nPassage: After starting 0-13 and looking most likely to become the second team in NFL history to go 0-16 after the 2008 Detroit Lions, the Colts would finally win a game. Having a career day, Donald Brown and a strong defense would deny Tennessee any hope of a win as the team improved to 1-13, allowing them to avoid becoming the third team in NFL history to finish a season winless, after the 2008 Detroit Lions and the 1976 Tampa Bay Buccaneers.\nA:" }, { "from": "gpt", "value": "How many teams finished a winless season?" } ]
[ { "from": "human", "value": "instruction:\nIn 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.\nquestion:\nArticle: The interview had been going on for about 20 minutes and everything seems to be going well.Then, suddenly, the interviewer asks an unexpected question, \"Which is more important, law or love?\" Job applicants in the west increasingly find themselves asked strange questions like this.And the signs are that this is beginning to happen in China. Employers want people skilled, enthusiastic and devoted.So these are the qualities that any reasonably intelligent job applicants will try to show no matter what his or her actual feelings are.In response, employers are increasingly using questions which try and show the applicant's true personality. The question in the first paragraph comes from a test called Kiersey Personality Sorter.It is an attempt to discover how people solve problems, rather than what they know.This is often called aptitude testing. According to Mark Baldwin of Alliance many job applicants in China are finding this type of questions difficult. When a Chinese person fills out an aptitude test he or she will think there is a right answer and they may fail because they try to guess what the examiner wants to see. This is sometimes called the prisoner's dilemma .Applicants are trying to act cleverly in their own interest.But they fail because they don't understand what the interviewer is looking for.Remember that in an aptitude test, the correct answer is always the honest answer. \n Question: The writer wrote the passage to _ . \n Options: (A) give you a piece of advice on a job interview. (B) tell you how to meet a job interviewer (C) describe the aptitude test. (D) advice you how to find a job\nanswer:\nA\n\n\nquestion:\nArticle: Most of us are the only child in our family. We have no brothers or sisters. Our family mainly _ our mom,our dad and us. We are growing up in a world differently from our parents'. And we will be the future leaders of China. Some day we have to work hand in hand with each other and make China more and more beautiful. So we must learn to love each other like brothers and sisters. It's hard to think how difficult life would be if we had a sibling(,).We never have to share anything at home. Of course, we might have cousins, but we don't have to live with them! Our parents try to give us the best, and the best doesn't need sharing between two or three children. Do we ever ask ourselves if we are spoiled? A recent study has found that many children don't know how to love others! We don'r know the value of money. We don't know how hard our parents are to support us. We don't want others to regard us as spoiled, do we? Well, why not start now to help our parents at home, share a game with one of our friends or value the opinions of our classmates, even if we don't always agree? In a word, we must learn to love each other! \n Question: As Chinese teenagers, what's our duty in the future? \n Options: (A) To save money (B) To learn to love each other (C) To look after our brothers and sisters (D) To make China more and more beautiful\nanswer:\nD\n\n\nquestion:\nArticle: One day a lady saw a mouse running across her kitchen floor. She was very afraid of mouse, so she ran out of the house, got into a bus and went to the shops. There she bought a mousetrap. The shopkeeper said to her, \"Put some cheese in it and you will soon catch that mouse.\" The lady went home with her mousetrap, but when she looked in her cupboard, she could not find any cheese in it. She did not want to go back to the shop, because it was very late, so she cut a picture of some cheese out of a magazine and put that in the trap. Surprisingly, the picture of the cheese was quite successful! When the lady came down to the kitchen the next morning she found a picture of a mouse in the trap beside the picture of the cheese \n Question: What would be the best title of the story? \n Options: (A) A clever mouse (B) A successful way (C) A fine match (D) A clever lady\nanswer:\n" }, { "from": "gpt", "value": "C\n\n\n" } ]
[ { "from": "human", "value": "Instructions: The input is a conversation between an automated system and a user looking for suggestions for pubs, restaurants and coffee shops in Cambridge. In the dialogue, the user may provide some criteria for the type of place they want such as price range, cuisine, etc. Similarly, the user may ask details of the place suggested by the system such as phone number, address, etc. Given such a dialogue, output a summary of the dialogue stating the criteria provided and details seeked by the user in this dialogue. The summary should strictly be in second person point of view. The summary should not contain any information that was not present in the conversation.\nInput: System: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?'\nUser: 'i want to know the pub with a internet connection and a tv i just want to know the addresses phone number and the price range'\nSystem: 'The Bakers is a great pub with an internet connection and a television.'\nUser: 'uh i want the address the phone number and the price range'\nSystem: 'The Bakers is located on 176 East Road and its phone number is 01223304121. The price for main courses ranges from 6 pounds to 8 pounds 49 and the price for a cheapest pint of beer is 2 pounds 25.'\nUser: 'yeah thanks a lot i got the information thank you goodbye'\n\nOutput:" }, { "from": "gpt", "value": "You want to find a pub and it should have an internet connection and have TV. You want to know the address, phone number, and price range." } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. Your task is to classify the conversation either convey 'No emotion' or 'Happiness' by providing '1' and '0', respectively.\n\n Person1: Which way is the dining car ? \n Person2: Two cars forward . \n Person1: What time will breakfast be served ? \n Person2: 7:00 , sir . \nOutput:" }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "Instructions: In this task, you will be shown a conversation and a question. You need to write an implausible answer to the question. Even though there exist multiple wrong answers, we only need a single wrong answer. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\nInput: W: Today in the studio we have Alberto Cortez, the well-known Brazilian advocate of the anti-global movement. He's here to talk about the recent report, stating that by 2050 Brazil will be the one ot the word's wealthiest and most successful countries. Alberto, what do you say to the report? M: You know this isn't the first time that people are saying Brazil will be a great economic power. The same thing was said over a hundred year ago. But it didn't happen. W: Yes, but you must admit the world's a very different place now. M: Of course. In fact I believe there's maybe some truth in the prediction this time around. First of all, though, we must remember the problems facing Brazil at the moment. W: Such as...? M: There's an enormous gap between the rich and the poor in this country. In Sal Paulo, you can see shopping malls full of designer goods right next door to the slam areas without proper water and electricity supplies. A lot of work needs to be done to help people in those areas improve their lives. W: What needs to be done? M: Education, for example. For Brazil to be successful, we need to offer education to all Brazilians. Successful countries like South Korea and Singapore have excellent education systems. Brazil needs to learn from these countries. W: So you are hopeful for the future. M: As I said earlier, I'm hopeful. This isn't an easy job. We need to make sure that these important opportunities for Brazil aren't wasted, as they were in the past., Question: What does the recent report say about Brazil?\nOutput:" }, { "from": "gpt", "value": "It will face challenges unprecedented in its history." } ]
[ { "from": "human", "value": "You are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to choose the correct answer to the question based on the passage. Answer of the question cannot be found directly from the passage, it is indirectly indicated in the passage. Do not answer with words other than the two options, and do not answer with option titles(e.g. \"option1\" or \"1\" are not acceptable answers.)\n\nExample Input: Passage: I jog in the early mornings because it gets hot very quickly in Phoenix . I spend quite a bit on money on jogging shoes because good support is necessary to keep one from being injured by the repetitive force on one 's body . So I dress in shorts , a sleeveless shirt and jogging shoes . I prepare a one quart jug of water that I carry in one hand and I prepare a second bottle for later use . Trees are so scarce in Phoenix , that any growth of deciduous trees is scenic . I jog at a pace that results in one mile traveled in 7.5 minutes . If I complete the mile in under 8 minutes , I get 4 \" points \" on a scale from a book on Aerobics that I bought years ago . At the 1.5 mile point , the path has returned me to my car and I change my used water bottle for the second one that I had prepared . I then jog the path one more time and I am finished is less than 24 minutes having acquired a total of 12 \" points \" The author of the book claimed that 30 points per week would keep my circulatory and respiratory systems in good shape , so I hit my weekly requirements if I jog only 3 times per week . Then I drive home and shower . Question: What does the the path do through the scenic trees? Option1: Winds through Option2: Travels over\nExample Output: Winds through\n\nExample Input: Passage: One morning Jeff was late for work because his alarm clock did n't wake him up . `` It must be out if batteries . '' Jeff said , `` ill go to the store after work and pick up some batteries . '' His boss was very upset that Jeff did not show up for work on time that day . so Jeff was told to return to his post and get to work or he will be fired . When Jeff got home from work , he went to the store to pick up some alarm clock batteries . The lady at the store said that they did n't sell batteries and that Jeff should try another store that was close to them . He got the batteries and went home . Jeff walked into his room and opened up the alarm clock , he took the old batteries out and replaced them with the new ones . Lastly he closed up the alarm clock and set it for the correct time that he had to wake up for work the next morning . Question: When did Jeff get back in his car? Option1: after setting the alarm Option2: after visiting the store\nExample Output: after visiting the store\n\nExample Input: Passage: I had to get up this morning and get the coffee ready . While it was waiting , I fed the cat , and made sure she was n't near the front door , because I did n't want to let her out . The paper usually came before I woke up anyway , so I did n't have any trouble finding it outside . I saw a light-colored plastic bag , which is usually what they came in , and could see the newspaper through the bag . I had to wear sunglasses just to go out for about 30 seconds , because I did n't think my eyes would be able to take it . I was glad when I took the paper out of the bag as I walked inside . It was much drier than the one I had gotten the day before ! Question: What was close to the sidewalk this time? Option1: The cat. Option2: Probably the newspaper.\nExample Output:" }, { "from": "gpt", "value": "Probably the newspaper.\n\n" } ]
[ { "from": "human", "value": "In this task, you're given a statement, further information available on a particular linked term from the statement, and a question. Your job is to generate the answer to the question by using the information provided. If there is no clear answer obtainable, output 'none'.\n\nInput: Consider Input: Context: Her next big screen venture was the indie Dare which was an official selection of the 2009 Sundance Film Festival. Link Information: none Question: In 2009, how many films were officially selected by the film festival that had selected the indie film Rossum appeared in that year?\n\nOutput: Answer: none\n\n\nInput: Consider Input: Context: Both Frankie Laine and Elvis Presley, among others, recorded versions of Robbins' song \"You Gave Me a Mountain\", with Laine's recording reaching the pop and adult contemporary charts in 1969. Though Elvis never recorded any of Robbins' songs in the studio, he was a big fan and recorded \"You Gave Me a Mountain\" live in concert several times; it appeared on 15 Presley albums. Link Information: none Question: Which Elvis Presley album was the first to contain \"You Gave Me a Mountain\"?\n\nOutput: Answer: none\n\n\nInput: Consider Input: Context: \"Written in the Stars\" was used by Major League Baseball for their commercials Link Information: It was also chosen by WWE as its theme song for WrestleMania XXVII Question: Which American sport organization that used \"Written in the Stars\" had been in operation first?\n\n" }, { "from": "gpt", "value": "Output: Answer: Major League Baseball\n\n\n" } ]
[ { "from": "human", "value": "In this task, you need to provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are coarse labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e tagset of this corpus is - \n '.': Period symbol is used for symbols denoting Punctuations/Separations such as comma, period, backticks etc., \n 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, \n 'ADP': Adposition is a cover term for prepositions and postpositions, \n 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, \n 'CONJ': A word used to connect clauses or sentences or to coordinate words in the same clause, \n 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, \n 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, \n 'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction, \n 'PRT': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech, \n 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, \n 'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object, \n 'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause, \n 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.\nOne example is below.\nQ: Sentence: `` Then I return to the United States for engagements at the Hollywood Bowl and in Philadelphia '' , he added {{ . }} \nWord: .\nA: .\nRationale: '--' is assigned the period (.) symbol since it denotes a separation.\nQ: Sentence: `` If you kick {{ too }} much , your leg gets kinda dead '' , he explained . \nWord: too\nA:" }, { "from": "gpt", "value": "ADV" } ]
[ { "from": "human", "value": "Definition: Given a sentence in English language, translate the sentence to Somali language keeping the meaning of the original sentence intact\nInput: English sentence: And he swore unto him.\nOutput:" }, { "from": "gpt", "value": "Boqorkiina wuu u dhaartay." } ]
[ { "from": "human", "value": "In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time.\n\nStatement: As figure 1.2 shows, household wealth accumulation has swelled relative to disposable personal income even as the flow of saving from current income has dwindled. Choices: 1. Household wealth accumulation has increased relative to disposable income, according to figure 1.2. 2. As seen in figure 1.2, the flow of saving from current income is increasing rapidly. 3. Household wealth accumulation has swelled by upwards of 75%, according to figure 1.2." }, { "from": "gpt", "value": "3" } ]
[ { "from": "human", "value": "instruction:\nIn this task, you are given a country name and you need to return the calling code of the given country. Your output must be formatted as a plus sign (+), followed by the calling code number\nquestion:\nSlovakia\nanswer:\n+421\n\n\nquestion:\nTonga\nanswer:\n+676\n\n\nquestion:\nSouth Africa\nanswer:\n" }, { "from": "gpt", "value": "+27\n\n\n" } ]
[ { "from": "human", "value": "In this task, you are given a premise sentence. Your task is to write a new sentence by substituting the subject and object (i.e., the input's subject should be output's object and vice versa.). The generated sentence must be fluent and shouldn't change the voice (i.e., passive or active) of the input.\nQ: The banker by the tourist helped the professor .\nA: " }, { "from": "gpt", "value": "The professor helped the banker ." } ]
[ { "from": "human", "value": "Instructions: In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis. It makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis. It makes you much more likely to believe the hypothesis is true. Your task is to output 'strengthener' or 'weakener' if the update strengths or weakens the hypothesis, respectively.\nInput: Premise: PersonX gives PersonY orders\nHypothesis: As a result, PersonX wants to make sure PersonY understands\nUpdate: As Person Y looks puzzled Person X says 'Go, get out of here'\nOutput:" }, { "from": "gpt", "value": "weakener" } ]
[ { "from": "human", "value": "Teacher:In this task, you're given the title of a five-sentence story, the first four sentences, and two options for the fifth sentence as a and b. Your job is to pick the sentence option that does not connect with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes less sense.\nTeacher: Now, understand the problem? Solve this instance: Title: Andy the Actor. Sentence 1: Andy had a play today. Sentence 2: He was playing as Romeo. Sentence 3: When he began to play the part, he forgot his line. Sentence 4: The crowd booed at him for his mistake. Choices: a. The doctor gave him allergy medicine. b. He ran off the stage in embarrassment and never acted again.\nStudent:" }, { "from": "gpt", "value": "a" } ]
[ { "from": "human", "value": "instruction:\nIn this task you will be given an arithmetic operation and you have to find its answer. The symbols of operators '+' and '-' has been swapped i.e you need to perform subtraction when you see a '+' symbol and addition in case of '-' symbol.\nquestion:\n2342 + 4498 - 5816 + 2604 - 6155 - 2683 - 1893 - 2482\nanswer:\n14269\n\n\nquestion:\n9096 - 7913 + 7375 + 7790\nanswer:\n1844\n\n\nquestion:\n6453 - 4160 - 6736 - 6049 - 2640 + 6379 - 8669 + 1499\nanswer:\n" }, { "from": "gpt", "value": "26829\n\n\n" } ]
[ { "from": "human", "value": "Definition: Given an open-ended topic (movie name, a persons name, an event, sports, etc) generate a simple trivia-type question.\nInput: desperate dan\nOutput:" }, { "from": "gpt", "value": "Desperate Dan appears in which comic book?" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a sentence in German, generate a new German 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.\nQ: Meine Mutter trank ihre Magie.\nA:" }, { "from": "gpt", "value": "Meine Mutter trank ihren Saft." } ]
[ { "from": "human", "value": "Given a statement and question, generate the answer to the question such that the answer is contained in the statement.\nQ: statement: Muscles in the upper arm shrinking causes a person 's elbow to straighten., question: What in the upper arm shrinking causes a person's elbow to straighten?\nA: " }, { "from": "gpt", "value": "Muscles" } ]
[ { "from": "human", "value": "In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining.\n\nQ: claim: Same sex relationships should have the same legal status as heterosexual relationships under EU law.\n perspective: Gay marriage is good for society\n\nA: support\n**\nQ: claim: Domestic intelligence agencies have a legitimate role to play in democracy.\n perspective: The government does not have the right to spy on its citizens\n\nA: undermine\n\nQ: claim: Sexist advertising must be banned.\n perspective: Policies should be established which ban the promotion of sexist attitudes in advertising.\n\nA:" }, { "from": "gpt", "value": "support\n**\n" } ]
[ { "from": "human", "value": "In this task, you are given a sentence containing a particular emotion. You must classify the sentence into one of the six emotions: 'joy', 'love', 'anger', 'fear', or 'surprise'.\nOne example is below.\nQ: i am ever feeling nostalgic about the fireplace i will know that it is still on the property\nA: love\nRationale: The word \"nostalgic\" could either indicate \"love\" or \"sadness\", but the fact that it is still on the property eliminates \"love\".\nQ: i was so nervous all i remember is my heart beating loudly and feeling insecure as others watched me from off stage\nA:" }, { "from": "gpt", "value": "fear" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. 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\nWhat is the part-of-speech tag of the word \"of\" in the following question: Which of the structures of Morocco is located a few kilometers south of Selouane ?\n" }, { "from": "gpt", "value": "IN" } ]
[ { "from": "human", "value": "Q: In this task, you have to identify the named entities (NER) which are the ingredients required given its directions. Named entities are the names of the items without their quantity.\nPlace olive oil, balsamic vinegar, and Dijon mustard in a medium bowl, stirring with a whisk until well combined. Add arugula to oil mixture; toss to coat greens. Top arugula mixture with cantaloupe and prosciutto.\nA:" }, { "from": "gpt", "value": "extra-virgin olive oil, balsamic vinegar, mustard, arugula, cantaloupe" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a abstract of article and corresponding title of an article. Your task is to generate label \"yes\" if title is right for article, otherwise generate \"no\".\nSee one example below:\nProblem: Abstract: This study was designed to determine the influence of a long-term, moderate-intensity treadmill training program on the distribution of blood flow within and among muscles of rats during exercise. One group (T) of male Sprague-Dawley rats trained for 1 h/day for 13-17 wk at 30 m/min on a motor-driven treadmill. A second group (UT) of rats was conditioned for 10 min/day for 4 wk at the same speed. Muscle succinate dehydrogenase activities were higher in T than UT rats indicating a significant training effect. Blood flows (BFs) in 32 hindlimb muscles or muscle parts and other selected organs were measured in the two groups with radiolabeled microspheres during preexercise and while the rats ran for 30 s, 5 min, or 15 min at 30 m/min on the treadmill. The data indicate 1) there were no differences in total hindlimb muscle BF between UT and T rats at any time; however, 2) T rats had higher preexercise heart rates and higher muscle BFs in the deep red extensor muscles, suggesting a greater anticipatory response to the impending exercise; 3) T rats demonstrated more rapid elevations in BF in the red extensor muscles at the commencement of exercise; 4) T rats had higher BFs in red extensor muscles during exercise, whereas UT rats had higher BFs in white muscles; and 5) T rats maintained higher BFs in the visceral organs during exercise. These findings demonstrate that exercise training results in changes in the distribution of BF within and among muscles and among organs during exercise. Specifically, data indicate the high-oxidative motor units that are primarily recruited in the muscles during the initial stages of moderate treadmill exercise receive higher blood flows in the trained rats; this presumably contributes to increased resistance to fatigue.. Title: Exercise blood flow patterns within and among rat muscles after training.\nSolution: yes\nExplanation: Title is appropriate for the given abstract because the focus of this abstract is cerebral white matter assesment.\n\nProblem: Abstract: Surgical treatments for dystonia have been available since the early 20th century, but have improved in their efficacy to adversity ratio through a combination of technologic advances and better understanding of the role of the basal ganglia in dystonia. The word \"dystonia\" describes a phenotype of involuntary movement that may manifest from a variety of conditions. Dystonia may affect only certain regions of the body or may be generalized. It appears to be critical to determine whether the etiology underlying the dystonia is \"primary\" (ie, occurring from a genetic or idiopathic origin) or \"secondary\" (ie, occurring as a result of structural, metabolic, or neurodegenerative disorders). Secondary dystonias are far more common than primary dystonias. Primary dystonias respond well to pallidotomy or deep brain stimulation of the internal segment of the globus pallidum, whereas secondary dystonias appear to respond partially at best. Limited historic and current data suggest that the thalamus may be a promising target for the treatment of secondary dystonias, but more careful, prospective, randomized studies are needed. Combinations of bilateral targets are possible with the current technology of DBS, but not widely used due to surgical morbidity and expense. This article reviews the surgical treatment of dystonia from past to present, with a focus on separating the outcomes for primary versus secondary and generalized versus cervical dystonia.. Title: Human and murine very small embryonic-like cells represent multipotent tissue progenitors, in vitro and in vivo.\nSolution:" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "instruction:\nIn this task, you need to remove all words of a given length in the sentence. The number of letters in a word determine its length, for example, the length of the word \"apple\" is 5.\nquestion:\nSentence: 'a large kitchen generously adorned with shiny metal surfaces'. Remove all words of length '7' in the given sentence.\nanswer:\na large generously with shiny metal surfaces\n\n\nquestion:\nSentence: 'people standing outside in a farm show type area and one kid holding plate of food'. Remove all words of length '1' in the given sentence.\nanswer:\npeople standing outside in farm show type area and one kid holding plate of food\n\n\nquestion:\nSentence: 'a police boat with lights going speeding along the water in front of the golden gate bridge'. Remove all words of length '1' in the given sentence.\nanswer:\n" }, { "from": "gpt", "value": "police boat with lights going speeding along the water in front of the golden gate bridge\n\n\n" } ]
[ { "from": "human", "value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to determine if the two sentences clearly agree/disagree with each other, or if this can't be determined. Indicate your answer as yes or no respectively.\n\nSentence 1: Look here, Tuppence, old girl, what is this going to lead to? Sentence 2: Tuppence, I am not interested in where you think this will lead.\nyes\n\nSentence 1: oh i'm sure personalities always come into play uh just in this size of organization Sentence 2: Personalities can be pushed aside and out of the way.\nyes\n\nSentence 1: Afraid to leave the project, to cross into another Sentence 2: Leaving the project would introduce financial instability.\n" }, { "from": "gpt", "value": "no\n\n" } ]
[ { "from": "human", "value": "In this task, you need to provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are coarse labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e tagset of this corpus is - \n '.': Period symbol is used for symbols denoting Punctuations/Separations such as comma, period, backticks etc., \n 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, \n 'ADP': Adposition is a cover term for prepositions and postpositions, \n 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, \n 'CONJ': A word used to connect clauses or sentences or to coordinate words in the same clause, \n 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, \n 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, \n 'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction, \n 'PRT': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech, \n 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, \n 'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object, \n 'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause, \n 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.\n\nLet me give you an example: Sentence: `` Then I return to the United States for engagements at the Hollywood Bowl and in Philadelphia '' , he added {{ . }} \nWord: .\nThe answer to this example can be: .\nHere is why: '--' is assigned the period (.) symbol since it denotes a separation.\n\nOK. solve this:\nSentence: {{ But }} what few containers they found were inadequate . \nWord: But\nAnswer:" }, { "from": "gpt", "value": "CONJ" } ]
[ { "from": "human", "value": "In this task you will be given a string and you should find the longest substring that is a palindrome. A palindrome is a string that is the same backwards as it is forwards. If the shortest possible palindrome is length 1 you should return the first character.\nOne example: gocogccocco\nSolution is here: gocog\nExplanation: The substring 'gocog' is the longest possible substring that is also a palindrome. So this is a good example.\n\nNow, solve this: dcdcedccecd\nSolution:" }, { "from": "gpt", "value": "dcd" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven a sentence and two mentions from the text (arguments), indicate a phrase (a verb or noun phrase) that describes the relationship between the provided arguments.\n\nSentence: 'Mayor Harrold said the Glendora Municipal Code states that the appointing authority for City Attorney shall be the City Council and no procedures are given .', Argument/Subject 1: 'city attorney', Argument/Subject 2: 'city council'\nOutput:" }, { "from": "gpt", "value": "be appoint by" } ]
[ { "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.\n--------\nQuestion: ['7967', '4893', '1855', 'i', 'R', '4131', 'd', '1589', 'e', 'D', 'R', '8327', '7369', 'X', '2539', 's', 'U', 'o', 'f']\n\nAnswer: 8\n\n\nQuestion: ['e', 'q', '8733', 'x', 'n', '9177', 'F', 'A', '2727', 'l', 'X', 'C', '6131', '3885']\n\nAnswer: 5\n\n\nQuestion: ['4231', 'T', '4865', 'X', 'Z', '4419', '9823', '3221', '4945', '7083', 'W', 'l', '5469']\n\nAnswer:" }, { "from": "gpt", "value": "8\n\n\n" } ]
[ { "from": "human", "value": "In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining.\n\nInput: Consider Input: claim: All Americans should have the right (be entitled) to health care.\n perspective: The government shouldn't pay for everyone's health care.\n\nOutput: undermine\n\n\nInput: Consider Input: claim: The United States should use the electoral college in presidential elections.\n perspective: The electoral college is just a violation of democratic principles and should be abolished.\n\nOutput: undermine\n\n\nInput: Consider Input: claim: The world should go vegan.\n perspective: There are ways other than giving up meat to help the environment.\n\n" }, { "from": "gpt", "value": "Output: undermine\n\n\n" } ]
[ { "from": "human", "value": "In this task the focus is on physical knowledge about the world. Given the provided goal task in the input, describe a process that would lead to the asked outcome. This process often involves physical motions with objects, such as moving them, arranging them in a certain way, mixing them, shaking them, etc. \n\nExample input: How do you remove keys from a computer keyboard for cleaning?\nExample output: Place the tip of a knife under the corner of a key and gently twist to pop it off.\nExample explanation: The process of removing keys from a keyboard for cleaning is descriptive and logical.\nQ: To determine how warmly you should dress,\nA:" }, { "from": "gpt", "value": "walk around your front yard to check the weather." } ]
[ { "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'.\n\n[EX Q]: As the drought season is here, we can ease the workload of the humidifier instead of increasing its working hour.\n[EX A]: False\n\n[EX Q]: If you are out of soap, it is better to use water than hand sanitizer.\n[EX A]: False\n\n[EX Q]: Bob's coffee mug was missing so he used a styrofoam cup.\n[EX A]:" }, { "from": "gpt", "value": "True\n\n" } ]
[ { "from": "human", "value": "In this task, you are given sentences from movie reviews. The task is to classify a sentence as \"POS\" if the sentiment of the sentence is positive or as \"NEG\" if the sentiment of the sentence is negative\n\nEx Input:\nBut it was n't .\n\nEx Output:\nNEG\n\n\nEx Input:\nAbout one in three gags in White 's intermittently wise script hits its mark ; the rest are padding unashamedly appropriated from the teen-exploitation playbook .\n\nEx Output:\nNEG\n\n\nEx Input:\nThe script feels as if it started to explore the obvious voyeuristic potential of ` hypertime ' but then backed off when the producers saw the grosses for Spy Kids .\n\nEx Output:\n" }, { "from": "gpt", "value": "NEG\n\n\n" } ]
[ { "from": "human", "value": "Part 1. Definition\nYou are given a dialog between 2 or more individuals. Within the dialog, there will be clues as to the names of the speakers. You will be asked at the end of the dialog to identify the name of one of the speakers.\nPart 2. Example\nSpeaker 1: It's been an hour and not one of my classmates has shown up! I tell you, when I actually die some people are gonna get seriously haunted! \nSpeaker 2: There you go! Someone came! \nSpeaker 1: Ok, ok! I'm gonna go hide! Oh, this is so exciting, my first mourner! \nSpeaker 3: Hi, glad you could come. \nSpeaker 2: Please, come in. \nSpeaker 4: Hi, you're Chandler Bing, right? I'm Tom Gordon, I was in your class. \nSpeaker 2: Oh yes, yes... let me... take your coat. \nSpeaker 4: Thanks... uh... I'm so sorry about Ross, it's... \nSpeaker 2: At least he died doing what he loved... watching blimps. \nSpeaker 1: Who is he? \nSpeaker 2: Some guy, Tom Gordon. \nSpeaker 1: I don't remember him, but then again I touched so many lives. \nSpeaker 3: So, did you know Ross well? \nSpeaker 4: Oh, actually I barely knew him. Yeah, I came because I heard Chandler's news. D'you know if he's seeing anyone? \nSpeaker 3: Yes, he is. Me. \nSpeaker 4: What? You... You... Oh! Can I ask you a personal question? Ho-how do you shave your beard so close? \nSpeaker 2: Ok Tommy, that's enough mourning for you! Here we go, bye bye!! \nSpeaker 4: Hey, listen. Call me. \nSpeaker 2: Ok! \nQuestion: What is the name or nickname of Speaker 2?\nAnswer: Chandler Bing\nExplanation: Speaker 4 asks Speaker 2 if they are Chandler Bing, and Speaker 2 responds 'yes'\nPart 3. Exercise\nSpeaker 1: Hey, everybody. Happy Thanksgiving! \nSpeaker 2: Hey happy Thanksgiving... Pheebs! \nSpeaker 1: Hey, what's going on Joe? \nSpeaker 2: I... I... I need a good lie. \nSpeaker 1: Oh okay. How about the whole \"man walking on the moon\" thing. You know? You. you could. You could see the strings people! \nSpeaker 2: No, no, no I need a good lie to explain why I wasn't at a work thing today. \nSpeaker 1: Ooh, honey. You stink at lying. \nSpeaker 2: I do not. \nSpeaker 1: Oh really. Okay. let me ask you something. Yesterday at the coffee house, I went to the bathroom and when I came back, my muffin was gone-who took it? \nSpeaker 2: Somebody opened the door to the coffee house and a raccoon came running in, went straight for your muffin and I said \"Hey don't eat that-that's Phoebe's\" and he said... He said... \"Joey you stink at lying.\" What am I going to do? \nSpeaker 1: Don't worry, don't worry. We'll come up with a good lie. I'll help you practice it. \nSpeaker 2: Oh great, that'd be great. Thank you. \nSpeaker 1: Sure, what... what was the work thing? \nSpeaker 2: Uh... \nSpeaker 1: \"Pick up grandma at the airport\"? \nSpeaker 2: Oh... man... What is the name or nickname of \nSpeaker 1?\nAnswer:" }, { "from": "gpt", "value": "Pheebs" } ]
[ { "from": "human", "value": "instruction:\nIn this task you will be given a list of integers. For every element in the list, if the element is even you should divide by 4, if the element is odd you should multiply by 4 then add 2. The output should be a list of numbers that is the result of applying that logic to the input list. You should not round any decimals in the output. Zero should be counted as an even integer.\nquestion:\n[75, -64, 44, 79, 47, -21, -52, -76, -30, 8, -48]\nanswer:\n[302, -16.0, 11.0, 318, 190, -82, -13.0, -19.0, -7.5, 2.0, -12.0]\n\n\nquestion:\n[-57, -32, -63, -68, 100, 8]\nanswer:\n[-226, -8.0, -250, -17.0, 25.0, 2.0]\n\n\nquestion:\n[82, -54, 89, -76, 26]\nanswer:\n" }, { "from": "gpt", "value": "[20.5, -13.5, 358, -19.0, 6.5]\n\n\n" } ]
[ { "from": "human", "value": "Given the prompt and a response, classify the them to \"yes\" if response is \"yes, and\" type. Otherwise classify it as \"no\". \"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...\"). 1 In short, a \"Yes, and\" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'. \n\nLet me give you an example: Prompt: I'm glad you came into my office today, young man. Look around you. Everything that's in here, I purchased. \n Response: Wow! You own everything in this office?\nThe answer to this example can be: yes\nHere is why: This is correct answer because response is in support with the prompt and extends the context from prompt.\n\nOK. solve this:\nPrompt: We're flying up to the sky, to the halls of where my ancestors look down upon us with judgement. \n Response: Human skin is the best kind of skin.\nAnswer:" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "In this task, you will be shown a conversation and a question. You need to write an implausible answer to the question. Even though there exist multiple wrong answers, we only need a single wrong answer. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\n--------\nQuestion: Woman: Hey. Are you leaving now? [ Yeah. ] Could you give me a ride to the train station? Man: Sure. Get in. Woman: Oh, I'm glad I caught you. My train leaves in about 20 minutes, and I don't have time to walk there. Man: No problem. Oh, I just got a text from my mom about her doctor's appointment. Woman: Wait. You're not going to text and drive, are you? Man: Yeah. I'm pretty good at it. Watch! Now, look here ... Woman: No, no. Hey, hey, to be honest, I feel uncomfortable with you trying to do both at the same time ... and it is against the law. Man: I've had a lot of practice. Woman: No really, I'll just walk. Pull over. I can catch the next train. Man: No, no, no. I'm almost finished with this text .... just a second. Woman: Watch out!! [ Scream ] Man: AHHHH! Oh, no. My car. Woman: Oh, no. OH NO!! Forget your car. The driver of the other car looks like a pro wrestler, and boy, does he look angry. Oh, no, oh no. He just punched that light pole and smashed his car window with his fist. Man: Oh, Hey, uh switch me seats? Woman: No. Forget it. I think it would be a good time for you to text or call the police. Man: Augh., Question: The woman suggests ___________.\n\nAnswer: catching the bus\n\n\nQuestion: M: It is Friday, isn't it? W: Yes, there will be a school concert this evening., Question: When will there be a school concert?\n\nAnswer: On Thursday evening.\n\n\nQuestion: M: Oops...I'm sorry, Mom, I broke another plate. I should probably let you finish. W: No, you go ahead. I got those dishes at a garage sale. Just be more careful!, Question: Where does the conversation take place?\n\nAnswer:" }, { "from": "gpt", "value": "In a garage.\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: 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.\nProblem:[[-2, -13, -8], [-27, 4], [-10, 7], [32, -36, -1, -21, -21], [48, 16, 19, 25, 43]]\nSolution:" }, { "from": "gpt", "value": "[-13, -27, 7, -441, 20425]" } ]
[ { "from": "human", "value": "In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\nQ: Beginning: Emily didn't have enough time to eat breakfast. Middle: Emily's stomach made grumbling sounds. Ending: Someone cracked a joke and Emily was embarrassed.\nA: " }, { "from": "gpt", "value": "Emily's anaconda made grumbling sounds." } ]
[ { "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 inputs i and A, where i is an integer and A is a list. You need to list all the elements of A preceding the last i elements. i will always have a value less than the length of A.\n\n5, ['5315', '8773', 'Z', '4873', 'r', '2929', 'K', 'y', '4997', '6739', 'U', 'j']\nOutput:" }, { "from": "gpt", "value": "5315, 8773, Z, 4873, r, 2929, K" } ]
[ { "from": "human", "value": "You 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.\n\n[Q]: When I'm deep frying a turkey, how defrosted should it be?\n[A]: It should be completely frozen, otherwise the oil may boil over and start a fire.\n\n\n[Q]: To find the center of a block of wood, you can\n[A]: Make measured lines at the corners facing outwards\n\n\n[Q]: Make wooden trash bin.\n[A]:" }, { "from": "gpt", "value": "Flip over a side table and line with trash bag.\n\n\n" } ]
[ { "from": "human", "value": "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.\nOne example is below.\nQ: I have bought several of the Vitality canned dog food products and have found them all to be of good quality. The product looks more like a stew than a processed meat and it smells better. My Labrador is finicky and she appreciates this product better than most.\nA: Good Quality Dog Food\nRationale: The customer talked about dog food which was good. So, it's a correct summary.\nQ: We love Kettle Chips Lightly Salted and don't feel guilty eating them! We used to buy them at Whole Foods but buying from Amazon has saved us money. We have purchased at least 3 times and have been happy with the chips and the delivery.\nA:" }, { "from": "gpt", "value": "the best chips ever" } ]
[ { "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.\nOne example is below.\nQ: 3, ['a', '34', 'f', '931', '7', '3432', '13245', '762']\nA: 931, 7, 3432, 13245, 762\nRationale: Here, all the elements except the first 3 from the list are '931', '7', '3432', '13245', and '762'.\nQ: 3, ['4823', '6003', '5841', 'B', 'W', 'k', 'v', '9897', 'b', 'f', 'H']\nA:" }, { "from": "gpt", "value": "B, W, k, v, 9897, b, f, H" } ]
[ { "from": "human", "value": "Q: In this task, you need to answer the given multiple-choice question on the physics. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.\nProblem: a water tank is one - fifth full . pipe a can fill a tank in 10 minutes and pipe b can empty it in 6 minutes . if both the pipes are open , how many minutes will it take to empty or fill the tank completely ? \nOptions: a ) 3 , b ) 6 , c ) 9 , d ) 12 , e ) 15\nA:" }, { "from": "gpt", "value": "a" } ]
[ { "from": "human", "value": "Given a sentence in Tagalog language, translate the sentence to English language keeping the meaning of the original sentence intact.\n\nTagalog sentence: Q: Ewan ko po kung alam niyo na yung headline ng Philippine Daily Inquirer ngayong umaga ang sinabi daw ni Executive Secretary Ermita na null and void ang mga pagdinig niyo dyan sa Senado dahil base raw po sa desisyon ng Supreme Court tungkol sa petition ni CHED Chairman Neri, kailangan maglathala muna kayo ng tinatawag ninyong rules of procedure o rules of inquiry dahil kasama daw yon sa due process bago kayo makapagsagawa ng mga pagdinig niyo at bago kayo makapagpa-contempt ng tao, Mr Senate President paano ito ngayon?" }, { "from": "gpt", "value": "Q: Senator, how is the party doing in light of the recent events? Well, of course we are, we've been meeting and it's a serious cause for concern for us considering that we feel the filing of the charges before the Regional Trial Court is contrary to law because it's not the Regional Trial Court that has jurisdiction over the cases of Senator De Lima but the Ombudsman and the Sandiganbayan. Plus of course the quality of the evidence taken from convicted drug traffickers and apparently that they may not be sued. There is a recommendation of the dropping of charges against them in this particular case. Maraming mga bagay na hindi tama at hindi tumutugma. The other consideration of course is the evidence itself. You have to have probable cause before you file charges. Based on the initial review of the information, there was no--they didn't show proof of the--well, where is the shabu, where are the drugs?" } ]
[ { "from": "human", "value": "Write a correct answer to the given question based on its associated fact. Make sure that your answer is contained in the associated fact. Don't be creative and introduce any new word that is not mentioned in the associated fact! Remember that the associated fact has been rearranged to form the question. So, the correct answer words must lie within the associated fact. The correct answer can be a word, phrase, or even a sentence.\n\nQ: Fact: thirst is used to make an animal realize that it needs to replenish H2O in its body. \nQuestion: Thirst shows an animal that it needs what?\n\nA: H2O.\n**\nQ: Fact: You can navigate through the Pacific with a compass. \nQuestion: What can you use to navigate the Pacific?\n\nA: compass.\n\nQ: Fact: Adoption of geothermal energy to produce electricity can reduce global warming. \nQuestion: Which of the following can help reduce global warming?\n\nA:" }, { "from": "gpt", "value": "Adoption of geothermal energy.\n**\n" } ]
[ { "from": "human", "value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with 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.\nQ: Sentence 1: A child holding a toy while walking on a lawn. Sentence 2: The man eats the pizza\nA: " }, { "from": "gpt", "value": "The toy is not on the lawn" } ]
[ { "from": "human", "value": "In this task you will be given a list of integers. You should only return an integer if the first digit is the same as the last digit in the number. If an integer has a single digit, then it should be returned. If there are no integers that start and end with the same digit then an empty list (\"[]\") should be returned.\nOne example is below.\nQ: [77, 999, 855, 10, 56, 121, 801]\nA: [77, 999, 121]\nRationale: The integers 77, 999, and 121 are the only integers in the input list that start and end with the same digit.\nQ: [-494, 598, -245, 225, -795, -353, -435, 138, 713, 688, 420, -249, 391, -681, -469, 440, 86, -617, 203, -950, 203]\nA:" }, { "from": "gpt", "value": "[-494, -353]" } ]
[ { "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: Although the provincial supplementary immunization activities (SIAs) conducted in 2009 and 2010 were able to reduce the transmissions from 2009 to 2011, larger values of R for children aged 0-6 years were observed after 2012, indicating that the benefits of the SIAs were short-lived. In addition, the transmissions from adults aged between 26 and 45 years PLOS ONE.\nOutput:" }, { "from": "gpt", "value": "1 - finding, 2 - finding, 3 - finding, 4 - finding" } ]
[ { "from": "human", "value": "Given a sentence, generate a most likely context or previous statement. The previous statement should be relevant to the given statement.\n\n[EX Q]: Outside, a large tank backs up as a long, black convertible car pulls to a stop.\n[EX A]: As the dust settles, the bearded man lifts a stone block off the goateed man who lies motionless.\n\n[EX Q]: Someone stands beside him holding a gun to his cheek.\n[EX A]: Now alone, the thin gunman peers around his pillar at the mezzanine.\n\n[EX Q]: They extend the hand washing to their wrists.\n[EX A]:" }, { "from": "gpt", "value": "The person scrubs their hands thoroughly with the soap.\n\n" } ]
[ { "from": "human", "value": "Instructions: In this task, based on the given context word, you are asked to create a pair of sentences each containing a blank (_) and their corresponding answer. The sentence pair should look similar, and should be about two related but different objects; for example \"trophy\" and \"suitcase\". Additionally, the two sentences must be different in terms of trigger words (e.g., \"small\" and \"big\") which express contrasting properties about the two objects. The answer must not be associated with the trigger word; instead, it should depend on the context present in twin sentences. Also, the answers should not be ambiguous. For each sentence, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals and proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style or phrase in twin sentences. E.g., a contrasting sentence can always be created using simple negation i.e. by adding not, never, etc. Instead, try to increase diversity. Both twin sentences must contain at least 15 and at most 30 words. Twin sentences must have at least 70% overlapping words. You must utilize the given context word while writing the twin sentences. Each of the twin sentences must contain only one blank. Make sure that ObjectX and Y have the same number e.g. when ObjectX is singular, ObjectY must be singular, too. The two objects (ObjectX & ObjectY) should be used ONCE in each sentence. Here is a list of contrastive words that may be used as trigger words. You should create more such trigger words and use them in your twin sentences.\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\nInput: Context Word: talkative.\nOutput:" }, { "from": "gpt", "value": "Sentence 1: The talkative crowd moved from the library to the parlor since the _ forbade talking out loud. \nAnswer1: library. \nSentence 2: The talkative crowd moved from the library to the parlor since the _ allowed talking out loud. \nAnswer2: parlor." } ]
[ { "from": "human", "value": "TASK DEFINITION: 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\nPROBLEM: What is the part-of-speech tag of the word \"what\" in the following question: On what type of field is the Armed Forces Bowl held ?\n\nSOLUTION: WP\n\nPROBLEM: What is the part-of-speech tag of the word \"which\" in the following question: Which country appeared at the tournament previously first ? The one that has a team which wears white , green and orange and has a nickname coming from the Dama gazelle , or one with a team which is nicknamed the Super Eagles ?\n\nSOLUTION: WDT\n\nPROBLEM: What is the part-of-speech tag of the word \"on\" in the following question: Which writer on the Pacific Ocean Blue album was born on October 16 , 1948 ?\n\nSOLUTION:" }, { "from": "gpt", "value": "IN\n\n" } ]
[ { "from": "human", "value": "Definition: In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.\nInput: onesevensixsixnineninefivetwonineeighttwo\nOutput:" }, { "from": "gpt", "value": "17669952982" } ]
[ { "from": "human", "value": "TASK DEFINITION: Given an trivia question precisely answer the question with a word/phrase/name. External resources such as Wikipedia could be used to obtain the facts.\nPROBLEM: Taylor Hawkins plays which instrument in the Foo Fighters?\n\nSOLUTION: drums\n\nPROBLEM: Fe is the chemical symbol for what metal?\n\nSOLUTION: iron\n\nPROBLEM: NOW, what I want is Facts. Teach these boys and girls nothing but Facts, are the opening sentences of Dickens' 'Hard Times'. Who says them?\n\nSOLUTION:" }, { "from": "gpt", "value": "gradgrind\n\n" } ]
[ { "from": "human", "value": "Teacher: In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis, that is, it makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis, that is, it makes you much more likely to believe the hypothesis is true. Your task is to answer with 'strengthener' or 'weakener' if the update strengthens or weakens the hypothesis, respectively.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nPremise: Old man crafting something in his workshop.\nHypothesis: An old man is working.\nUpdate: The man is serious and is surrounded by workers.\nSolution: strengthener\nReason: If the old man is serious and surrounded by workers, it is more likely that he is working.\n\nNow, solve this instance: Premise: Erotic show with guests looking onwards.\nHypothesis: Some guests are relatives.\nUpdate: There are two people who look identical to one of the dancers.\nStudent:" }, { "from": "gpt", "value": "strengthener" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given an input list A. You need to find all the elements of the list that are alphabets in the same order as they appear in the list A. Do not change their case/capitalization.\nProblem:['I', '8601', '7835', '3951', 'Y', '3771', '9365', 'h', 'D', 'v', '1585', 'q', 'G', 'A', '9543', '717', '4679', '9539', 'u', '9897', '7121', '9563', 'h', 't', 'x', '9007', '961']\nSolution:" }, { "from": "gpt", "value": "I, Y, h, D, v, q, G, A, u, h, t, x" } ]
[ { "from": "human", "value": "You will be given a sentence. Check whether the sentence is grammatically correct and is meaningful. If the sentence is grammatically correct, then answer with '1', otherwise answer with '0'.\n\nQ: The farm passed to John.\n\nA: 1\n**\nQ: It's probable that in general he understands what's going on.\n\nA: 1\n\nQ: Lora buttered the toast with unsalted butter.\n\nA:" }, { "from": "gpt", "value": "1\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.\nYou 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.\n\npassword = a\nSolution: 5\nWhy? Using 5 steps, it can become a strong password\n\nNew input: password = Buq\nSolution:" }, { "from": "gpt", "value": "3" } ]
[ { "from": "human", "value": "Craft one incorrect answer. In doing so, try to use words from the context as much as possible, or by using similar words used in the correct answer. DO NOT craft nonsensical or off-topic incorrect answers, such that the incorrect answers can be directly excluded without reasoning according to the context. Try to make your responses similar to the given correct answer. To this end, try to keep both the length and the style as similar as possible between the correct and the incorrect answer. To make your incorrect answers more difficult, try to incorporate words from context. To avoid being predictable or repetitive, try to add more variations and complexity.\n\nContext: God damn it , it did n't . I could n't even find a stairwell . I ran up three levels -- on the parking ramp -- till I found a stairwell that could spring me out of that horribly hot hell . Once I was outside , I realized I was about a quarter - mile from my car . \nQuestion: What may have happened before I was looking for a stairwell? \nCorrect Answer: The building was too hot for me." }, { "from": "gpt", "value": "My car was being stolen outside." } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. 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.\n\n[{'first': -97, 'second': -74}, {'first': 27, 'second': 21}, {'first': -72, 'second': 96}, {'first': -79, 'second': -6}]\n" }, { "from": "gpt", "value": "[{'first': -97, 'second': -74}, {'first': -79, 'second': -6}, {'first': -72, 'second': 96}, {'first': 27, 'second': 21}]" } ]
[ { "from": "human", "value": "Teacher:You are shown a conversation between a user and system. Identify who has spoken the indicated sentence based on the conversation.\nTeacher: Now, understand the problem? Solve this instance: Sentence1: I have 19 places to stay with 4 stars and parking, which area would you prefer? Sentence2: OK, I don't need a room right now, but can I have the post code and phone number for Acorn? Sentence3: I need to find a 4 star hotel that also has free parking. Sentence4: Are there any guesthouses with free wifi? Sentence5: It is moderately priced. I don't have an exact price. Sentence6: I would like to be in the north area. Sentence7: How much per night? Sentence8: Thanks! That's all I needed today. Bye! Sentence9: Yes, all 7 guesthouses have internet available. What price range are you looking for? Sentence10: How about Acorn Guest House? Sentence11: There are no hotels that fit your criteria. However, there are 7 guesthouses available. Would you like me to book one of those for you? Sentence12: Sure. Postcode cb41da and phone number 01223353888. Is there anything else I can do for you? Sentence13: Thank you, have a great day. Sentence14: Oh, cool. It really doesn't matter. Which would you recommend? Question: Who has spoken the sentence 4? (A) User (B) System\nStudent:" }, { "from": "gpt", "value": "Answer: (A) User" } ]
[ { "from": "human", "value": "instruction:\nGiven the sentence, generate \"yes, and\" response. \"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...\"). 1 In short, a \"Yes, and\" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'. \nquestion:\nThere's another possibility. We were going to use animatrons in some of the Epcof installations. These two just do the same thing over and over again.\nanswer:\nYou're suggesting that we chain up these two people in a box and have them perform for people?\n\n\nquestion:\nJosephenia, what are you doing? Why are you talking to that man?\nanswer:\nCan't I talk with someone in private for one second?\n\n\nquestion:\nYou can stand there and tell me about your lake or you can help Toaster Strudel and I find our singing rat.\nanswer:\n" }, { "from": "gpt", "value": "I'm sorry. Who are you sir? We haven't met.\n\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. 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\nWhich is true about reproduction for both an amoeba and a paramecium? \n (A) Both can conjugate. (B) Neither can conjugate. (C) An amoeba can conjugate, but a paramecium cannot. (D) A paramecium can conjugate, but an amoeba cannot.\n" }, { "from": "gpt", "value": "D" } ]
[ { "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 which is either in the Swedish language or English language. You task is to identify the language of input sentence. Input sentence can be in Swedish or English language only and also it cannot have two languages at a time.\n\nAccording to its President, it is in a position to do so.\nOutput:" }, { "from": "gpt", "value": "English" } ]
[ { "from": "human", "value": "In this task you will be given a list of integers. For every element in the list, if the element is even you should divide by 4, if the element is odd you should multiply by 4 then add 2. The output should be a list of numbers that is the result of applying that logic to the input list. You should not round any decimals in the output. Zero should be counted as an even integer.\n\nExample input: [5, 8, 9, 3, 7]\nExample output: [22, 2.0, 38, 14, 30]\nExample explanation: The odd numbers, 5, 9, 3, and 7 were multiplied by 4 then added 2. The even number eight was divided by 4.\nQ: [82, -54, 89, -76, 26]\nA:" }, { "from": "gpt", "value": "[20.5, -13.5, 358, -19.0, 6.5]" } ]
[ { "from": "human", "value": "Q: In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to provide one question which clarifies the input question and it has one unique answer, and also provide an answer to the generated question. Generated question and answer should be separated with a new line.\nNumber of members of the house of representatives?\nA:" }, { "from": "gpt", "value": "How many total members of the house of representatives are there, including non-voting members? \n 441" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence.\nSee one example below:\nProblem: Who did the Han Chinese want to help the Khitan no I mean the Mongols fight?\nSolution: Who did the Han Chinese want to help the Mongols fight?\nExplanation: The input initially means Khitan and then changes to Mongols, hence this is correct.\n\nProblem: Where is the rock, no, gravel from that is found in xenoliths?\nSolution:" }, { "from": "gpt", "value": "Where is the gravel from that is found in xenoliths?" } ]
[ { "from": "human", "value": "Detailed Instructions: Read the given sentence and if it is a general advice then indicate via \"yes\". Otherwise indicate via \"no\". advice is basically offering suggestions about the best course of action to someone. advice can come in a variety of forms, for example Direct advice and Indirect advice. (1) Direct advice: Using words (e.g., suggest, advice, recommend), verbs (e.g., can, could, should, may), or using questions (e.g., why don't you's, how about, have you thought about). (2) Indirect advice: contains hints from personal experiences with the intention for someone to do the same thing or statements that imply an action should (or should not) be taken.\nProblem:I think you know this is actually damaging your health so I think relaying in your support system is important .\nSolution:" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "In this task you are given a tweet that contains some form of irony. You must classify the type of irony the tweet has. Label the tweets (\"polarity\",\"situational\",\"other\") based on the irony they have. Situational irony happens when a situation fails to meet some expectations, Label these instances as \"situational\". polarity irony happens when irony is achieved by inverting the intended sentence, Label these instances as \"polarity\". There are other kinds of ironies that are neither polarity nor situational, Label these instances as \"other\". Note that URLs in the text have been replaced with [Link].\n\nLet me give you an example: crushes are great until you realize they'll never be interested in you.\| :p\nThe answer to this example can be: situational\nHere is why: Instance describes a situations that fail to meet expectations.\n\nOK. solve this:\nSorry this doesn't make any sense why make it even more tough? That's going to produce more players.. [Link]\nAnswer:" }, { "from": "gpt", "value": "other" } ]
[ { "from": "human", "value": "You are given a sentence and a question in the input. If the information provided in the sentence is enough to answer the question, label \"Yes\", otherwise label \"No\". Do not use any facts other than those provided in the sentence while labeling \"Yes\" or \"No\". There are only two types of valid responses: Yes and No.\n\n[Q]: Sentence: Today he had to go to school and he wasn't very happy about that. \nQuestion: What did John get in trouble for?\n[A]: No.\n\n\n[Q]: Sentence: Now, I like butterflies!. \nQuestion: Where did the child go when he saw the butterflies?\n[A]: No.\n\n\n[Q]: Sentence: They called the police to get an accident report. \nQuestion: What happened after the friends left the mall?\n[A]:" }, { "from": "gpt", "value": "Yes.\n\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nThe task is to generate text based off of an event. For the given event, there will be a person who does the action in the event (usually PersonX). Your task is to write that persons intent behind doing the event, i.e. why did the person do that action.\n\nPersonX gives PersonY a lot\nOutput:" }, { "from": "gpt", "value": "to be generous" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a text which is the body of the document. Indicate your answer as \"Yes\" if the text is about a person, otherwise indicate your answer as \"No\". Don't generate anything else apart from \"Yes\" or \"No\". Pay attention that for your answer to be \"Yes\", the passage should be generally about a person. Mentions of people in the text don't necessarily mean the text is about a person.\nQ: Text: London Fields is the upcoming film adaptation of the 1989 novel of the same name by Martin Amis directed by Mathew Cullen. The film stars Billy Bob Thornton as Sampson a terminally ill writer who has suffered from writer's block for twenty years. The cast also includes Amber Heard Jim Sturgess Jaimie Alexander and Theo James with the cameo appearance of Johnny Depp.\nA:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "In this task you will be given a list of strings and you need to concatenate them.\nExample: ['a', 'b', 'c']\nExample solution: abc\nExample explanation: The strings 'a', 'b', 'c', got concatenated into the string 'abc'. So this is a good example.\n\nProblem: ['became', 'm', 'not', 'E', 'make', 'H', 'at', 'y', 'n', 'the', 'u', 'him.d', 'T']\n" }, { "from": "gpt", "value": "Solution: becamemnotEmakeHatyntheuhim.dT" } ]
[ { "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 position of all the numerical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no numerical element is in the list.\nOne example: ['238', 'h', '92', 'U', '2799']\nSolution is here: 1, 3, 5\nExplanation: Here, the numerical elements in the input list are '238', '92' and '2799' and they are at positions '1', '3', and '5', respectively.\n\nNow, solve this: ['7723', '4661', 't', 'J', 'f', 'T', 'N', 'l', 'i', 'F', 's', '7499', 'U', '6799', '5673', '11', 'g', 'A', '9973', '1141', '9241', '6959', 'g', 'h', '6359', '2537']\nSolution:" }, { "from": "gpt", "value": "1, 2, 12, 14, 15, 16, 19, 20, 21, 22, 25, 26" } ]
[ { "from": "human", "value": "Teacher: 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.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nRope and its Usage\nSolution: Intambo nomsebenzi ewenzayo.\nReason: 'Intambo' means rope, 'nomsebenzi ewenzayo' roughly translates to 'the work it does', which is a native way of phrasing it.\n\nNow, solve this instance: A considerable coating of snow and ice on rigging, super-structure or on deck will obviously affect the stability of a ship adversely.\nStudent:" }, { "from": "gpt", "value": "Uungisiso lomaluko lwekhephu kunye nomkhenkce kuxhobiso kwisakhiwo esingaphezulu kwesinye okanye kumgangatho onokuba kungakukona kuchaphazela ukwenza umchasi kwinqanawa." } ]
[ { "from": "human", "value": "Construct a question that every answer in the list is correct and reasonable for it.\n\nEx Input:\ndoctor/dentist, hairdress./barber, masseuse, nurse, tailor/clothing, manicurist\n\nEx Output:\ntell me an occupation where you have to touch your customers.\n\n\nEx Input:\nunderwear, jeans, shoes, socks, t-shirt, jacket, ring\n\nEx Output:\nname something you wear that you don't take to the dry cleaners.\n\n\nEx Input:\nburn pizza, wrong topping\n\nEx Output:\n" }, { "from": "gpt", "value": "name a mistake a pizza chef might make the first day on the job.\n\n\n" } ]
[ { "from": "human", "value": "Based on the given question and tppic, give an answer. The answer is available on on the internet. The questions are mostly centered around a single named entity.\n\nconcept: Brazil question: what language brazil use?\n['Portuguese Language']\n\nconcept: Henry Hudson question: where did henry hudson travel?\n['Hudson Bay']\n\nconcept: Thailand question: what kind of currency do they use in thailand?\n" }, { "from": "gpt", "value": "['Thai baht']\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven a premise, an initial context, an original ending, and a counterfactual context, the task is to generate a new story ending aligned with the counterfactual context and as close to the original ending as possible. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context and the story's general plot. The original ending is the last three sentences of the story. Also, a counterfactual context is a slight modification to the initial context. You should write a new story ending that edits the original story ending as little as possible to regain coherence with the counterfactual context. To sum up, you should write the last three sentences of a story based on the premise(first sentence) and the counterfactual context(second sentence) of the story.\n\nPremise: Amy was watching TV when she found a scary movie. \n Initial Context: She and her brother watched the whole film. \n Original Ending: They each pretend not to be afraid. When it was time to sleep Amy was scared to go into her room. She fell asleep hiding under her bed with a flashlight. \n Counterfactual Context: She was much braver than her brother.\nOutput:" }, { "from": "gpt", "value": "He pretended he wasn't afraid. When it was time to sleep Amy's brother was scared to go into her room. He fell asleep hiding under his bed with a flashlight. " } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you're given a statement, the genre to which that statement belongs, and a label indicating if the statement should be agreed with (entailment), disagreed with (contradiction), or neither (neutral). Your job is to write a sentence that describes the genre that follows the tone with respect to the statement, as indicated by the label. If sentence X agrees with sentence Y, the can be concluded from one another. If sentence X disagrees with sentence Y, they can not be correct at the same time. The sentence must also belong to the genre specified.\n\nStatement: The Commission discusses these comments and any actions taken in reaction to them in the supplementary information provided when the Final Rules were published in the Federal Register on September 12, 1996 (61 Fed.\nLabel: entailment.\nGenre: government.\n" }, { "from": "gpt", "value": "These comments were discussed by the Commission and published on September 12, 1996." } ]
[ { "from": "human", "value": "Instructions: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. 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.\nInput: Sentence 1: The motorcyclist has reached the summit. Sentence 2: A person rides a motorcycle.\nOutput:" }, { "from": "gpt", "value": "A person rides a motorcycle fast." } ]
[ { "from": "human", "value": "In this task, you are given an input list A. You need to find all the elements of the list that are alphabets in the same order as they appear in the list A. Do not change their case/capitalization.\n\nQ: ['I', '6973', 'y', 's', '175', 'H', '7113', 'h', 'C', '8191', '2227']\n\nA: I, y, s, H, h, C\n**\nQ: ['J', '5903', '8183', '7039', 'X', '243', 'o', '5175']\n\nA: J, X, o\n\nQ: ['i', 'C', 'U', '8917', '9223', 'j', 'c', 'K', '2389', 'A', '1683', 'I', '4073', 'n', '337']\n\nA:" }, { "from": "gpt", "value": "i, C, U, j, c, K, A, I, n\n**\n" } ]
[ { "from": "human", "value": "In this task, a passage will be given and the goal is to identify an event from the passage. An event is defined as a single word representing something that happened, is happening, or may happen. An event can be factual or hypothetical, positive or negative, certain or uncertain. While most events are based on verbs, an event can also be based on a noun (ex. storm, snow, rainfall) or a copula verb (is, was, been, etc.). The event must not be a pronoun or an adjective. For noun events with multiple words, use the last word in the phrase as event.\n\nPassage: Japanese share prices got off to a strong start in post-holiday trading Wednesday, following a surge on Wall Street the previous day, brokers said. The Nikkei stock average gained 307.83 points, or 1.6 percent, from Monday in the first one hour to stand at 18,978.20 at 10 a.m. (0100 GMT).\ntrading\n\nPassage: Meanwhile, a Russian cargo vessel in the southern Adriatic picked up around 20 Albanian refugees navigating the waters in a rubber dinghy. \npicked\n\nPassage: Williams, whose case has prompted an international campaign for clemency, faces the death penalty for murdering four people unless the governor intervenes before Tuesday. Hollywood celebrities, including Jamie Foxx and Danny Glover, African-American leaders and opponents of the death penalty have championed Williams' case, citing his work against gang violence.\n" }, { "from": "gpt", "value": "case\n\n" } ]
[ { "from": "human", "value": "Predict the next word given an incomplete English Sentence.\n\nInput: Consider Input: it does really seem as if i must be dreaming well i'm sorry\n\nOutput: for\n\n\nInput: Consider Input: and yet his manners showed the effects of a sort of education if not\n\nOutput: a\n\n\nInput: Consider Input: bordered with wild rose bushes it's no wonder matthew and marilla are both a little odd living away back here by themselves trees aren't much company though dear knows if they were there'd be enough of them i'd ruther\n\n" }, { "from": "gpt", "value": "Output: look\n\n\n" } ]
[ { "from": "human", "value": "Part 1. Definition\nGiven the prompt and a response, classify the them to \"yes\" if response is \"yes, and\" type. Otherwise classify it as \"no\". \"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...\"). 1 In short, a \"Yes, and\" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'. \nPart 2. Example\nPrompt: I'm glad you came into my office today, young man. Look around you. Everything that's in here, I purchased. \n Response: Wow! You own everything in this office?\nAnswer: yes\nExplanation: This is correct answer because response is in support with the prompt and extends the context from prompt.\nPart 3. Exercise\nPrompt: Your children have a very special anniversary gift for you. \n Response: Oh, the apples of my eye. What do you have for Mommy?\nAnswer:" }, { "from": "gpt", "value": "yes" } ]
[ { "from": "human", "value": "Definition: 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'.\nInput: Person1: Mom , why do chinese people like to touch my head ? sometimes they even touch my cheeks . \n Person2:That is a part of chinese culture , if they think you are a lovely child , they touch your head and say , how cute you are . \n Person1: But i donor like it , not a bit , i am not a pet , i am a girl . \n Person2:Well , you get used to it , different countries have different manners . \n Person1: But i do not like anyone touch my head . \n Person2:They are just been in friendly , when you are in Roman , do as the Romans do , that means you need to adapt to your enviroment . \n Person1: What if everybody in the wheres goes crazy ? \n Person2:Then you might need to pretend to be a little crazy . \n Person1: Does this mean that if i might want those new European bitches , i am supposed to wonder run reget ? \n Person2:Do you think it is a ~ got give your brain , use it if you really cannot accept it people touch your head , keep distance from them , why not just wear your big flyby hat and ~ is anyone get close to you . \n Person1: That is my work , i will try it . \nOutput:" }, { "from": "gpt", "value": "formal" } ]
[ { "from": "human", "value": "Teacher: In this task, you are given a question containing a blank (_) and two options. You should pick the best option to answer the question. Please answer with \"A\" or \"B\".\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nKatrina gave Christine a stuffed animal for their birthday, but _ already had this one. (A) Katrina (B) Christine\nSolution: B\nReason: Since the blank is someone who received the gift and already had a stuffed animal, the answer must be \"Christine\".\n\nNow, solve this instance: The movers tried to store the bed in the garage but the _ was too large. (A) garage (B) bed\nStudent:" }, { "from": "gpt", "value": "B" } ]

Subsets and Splits

No community queries yet

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