Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "from": "human", "value": "instruction:\nGiven a set of four words, generate the category that the words belong to. Words are separated by commas. The possible categories are social gathering, accomodation, physical property, measurement unit, corporate, nutritional value, boats, police punishment, location (proximity), card games, outdoor sport activity, military rank, baby animals, weather, consumer product, animals, boxing terminology, food, chocolate food, bird, type of sandwich, date status, body part, ocean, employment activity, moral characteristic, elements, poker, computers, construction, guitar part, shady activities, physical activity, kitchenware, temperature, type of rigidity, emotional status, season, mode of transportation, window material, activity, emotional display, geographical property, fried food, store status, widespread, aesthetic characteristic, alcoholic drinks, secretary duty, direction, personal characteristic, and animal.\nquestion:\nstern, blunt, frank, precise\nanswer:\nmoral characteristic\n\n\nquestion:\nwaggle, pounce, eagle, fly\nanswer:\nanimal\n\n\nquestion:\npenalty, ticket, jail, fine\nanswer:\n" }, { "from": "gpt", "value": "police punishment\n\n\n" } ]
[ { "from": "human", "value": "You will be given three sentences. Read them, then identify a noun phrase (person, place, or thing) or event that is shared between all three sentences. As the output, write the span of the text corresponding to that phrase in each sentence. Keep the order of the sentences, that is, your answer should look like: 1: a phras from sentence 1e 2: a phras from sentence 2 3: a phrase from sentence 3\n\n1: But there was one character who remained a mystery : the Vision , to be played by Paul Bettany . 2: Meanwhile , as many Marvel fans know , Thursday was the eve of the new Netflix series Daredevil , and after a photoshopped first look at Charlie Cox 's iconic red Daredevil suit went out , Marvel put out a video of the real one . 3: Marvel Studios releases first looks at Paul Bettany as the Vision in Avengers : Age of Ultron and Charlie Cox in full Daredevil costume ." }, { "from": "gpt", "value": "1: Paul Bettany 2: Daredevil 3: Daredevil" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you need to answer 'Yes' if the given word is the longest word (in terms of number of letters) in the given sentence, else answer 'No'. Note that there could be multiple longest words in a sentence as they can have the same length that is the largest across all words in that sentence.\n\nSentence: 'a school bus sits parked as people walk by'. Is 'school' the longest word in the sentence?\n" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "In this task, you need to replace a letter in the sentence with another given letter.\nQ: Sentence: 'a city square at night with buildings around it'. Replace the letter 'i' with 'y' in the sentence.\nA: " }, { "from": "gpt", "value": "a cyty square at nyght wyth buyldyngs around yt" } ]
[ { "from": "human", "value": "Instructions: In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the letters E, C, and N respectively.\nInput: Sentence 1: Three people and a dog stand in front of a river on a cold day. Sentence 2: Three girls and a poodle are standing in front of the Nile River.\nOutput:" }, { "from": "gpt", "value": "N" } ]
[ { "from": "human", "value": "Teacher: In this task, you are presented with a term, a description of the term, and an expected answer ('yes' or 'no'). You should write a yes-no question about the given term such that the answer is the one provided to you (i.e., If the answer is \"No\", you should ask a question that its answer would be \"No\", and if the answer is \"Yes\", you should ask a question that its answer is \"Yes\". ). The question should have a definitive answer (as opposed to ambiguous or subjective questions, e.g., Is Batman a good movie?). Create a question such that its answer can not be found easily on a single web page (e.g., mentioned in a Wikipedia page). This can be accomplished if answering the question requires more than one fact (facts = statements that can be found on a Wikipedia page or Google). For example, answering the question 'did Aristotle use a laptop?', one needs the know about the invention of the laptop and the death of Aristotle. Avoid questions should not just compare the properties of objects (e.g., Is a door bigger than an elephant?) or those that refer to details in the given description.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nTerm: Cooking oil, Description: Oil consumed by humans, from vegetable or animal origin., Answer:No\nSolution: Can all types of cooking oil be poured?\nReason: This is a good question. For answering this question, you need to know different cooking oils and whether they can be poured.\n\nNow, solve this instance: Term: Justin Timberlake, Description: American singer, record producer, and actor, Answer:Yes\nStudent:" }, { "from": "gpt", "value": "Can Justin Timberlake ride Shipwreck Falls at Six Flags?" } ]
[ { "from": "human", "value": "In this task, you need to count the number of vowels (letters 'a', 'e', 'i', 'o', 'u') / consonants (all letters other than vowels) in the given sentence.\n--------\nQuestion: Sentence: 'two guys talking on their cell phones while drinking'. Count the number of vowels in the given sentence.\n\nAnswer: 14\n\n\nQuestion: Sentence: 'a man talking on a phone while standing in front of a toilet'. Count the number of vowels in the given sentence.\n\nAnswer: 19\n\n\nQuestion: Sentence: 'an elephant standing in water, bathing it's body'. Count the number of vowels in the given sentence.\n\nAnswer:" }, { "from": "gpt", "value": "13\n\n\n" } ]
[ { "from": "human", "value": "In this task, you will be presented with a question in Dutch language, and you have to write the location names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Identifier used for the location name - LOC. . There can be instances with no location name entity, then return 'None'.\n\nEx Input:\nKosten LPG-vervoer worden ' variabel '\n\nEx Output:\nNone\n\n\nEx Input:\nDe operatie tastte de stembanden van Stewart niet aan .\n\nEx Output:\nNone\n\n\nEx Input:\nOndanks de regen van de laatste dagen was mei een bijzonder zonnige maand .\n\nEx Output:\n" }, { "from": "gpt", "value": "None\n\n\n" } ]
[ { "from": "human", "value": "Given two sentences regarding the stereotypes of religions, determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.\nOne example: Target: Muslim \nMuslim people live all over the world. They are hateful toward women and children.\nSolution is here: stereotype\nExplanation: This is a stereotype because not every Muslim person is hateful towards women and children.\n\nNow, solve this: Target: Muslim \nThe Muslim woman wore a hijab. The woman worked as a scientist at the lab.\nSolution:" }, { "from": "gpt", "value": "anti-stereotype" } ]
[ { "from": "human", "value": "You are supposed to identify the category of a high-school level math question. There are five possible categories (1) algebra (2) arithmetic (3) measurement (4) numbers, and (5) probability. Use the following guidelines: (1) 'algebra' questions will typically contain letter variables and will ask you to find the value of a variable (2) 'arithmetic' questions will ask the sum, difference, multiplication, division, power, square root or value of expressions involving brackets (3) 'measurement' questions are questions that ask to convert a quantity from some unit to some other unit (4) 'numbers' questions will be about bases, remainders, divisors, GCD, LCM etc. (5) 'probability' questions will ask about the probability of the occurrence of something. A question must belong to only one category.\n\nConvert 8.958269 kilometers to centimeters.\nmeasurement\n\nWhat is prob of sequence ltr when three letters picked without replacement from lijjjotjjorjjl?\nprobability\n\nWhat is 1699 to the power of 1/6, to the nearest integer?\n" }, { "from": "gpt", "value": "arithmetic\n\n" } ]
[ { "from": "human", "value": "Teacher:You are asked to create a question containing a blank (_), based on the given context word. Your question must contain two related but different objects; for example \"trophy\" and \"suitcase\". The expected answer to your question must be one of the objects present in the sentence. The expected answer must not be associated with any specific word in the question; instead it should depend on the context present in the question. The expected answer should not be equally likely to fill the blank. For your question, there should be a agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals or proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style, pattern or phrases in each question, try to increase diversity by varying sentence structure, blank placement etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Object X and Y have the same number e.g. when ObjectX is singular, Object Y must be singular, too. The two objects (Object X & Object Y) should be used ONCE in your question. Here is a list of attributes and associated pair of contrastive words which may be used to create a valid question using the objects. You can use either of the contrastive words, but not both. You should think about more such attributes and associated words and use them in your question.\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\nTeacher: Now, understand the problem? Solve this instance: Context Word: foot.\nStudent:" }, { "from": "gpt", "value": "After walking barefooted, James washed his foot in the bowl of water and the _ got clean." } ]
[ { "from": "human", "value": "In this task, you're given a context passage, a question, and three answer options. Your task is to return an incorrect answer option to the question from the choices given. For all questions, only one of the three answer options is correct. Pick one of the two incorrect answer options as the output.\n\nExample Input: Context: Skylar kept Quinn from becoming a waitress after telling her it was a dead end job. \n Question: What will Quinn want to do next? \n Options: (A) go back to school (B) encourage Quinn to study (C) go back to college\nExample Output: A\n\nExample Input: Context: Sasha knew deep down inside that she would love to go camping. \n Question: How would you describe Sasha? \n Options: (A) hesitant to try something new (B) go camping (C) open to trying new things\nExample Output: B\n\nExample Input: Context: Casey shone Carson's shoes after Carson asked him to. \n Question: How would Casey feel afterwards? \n Options: (A) a shoe shiner (B) cleaning Carson's shoes (C) complete\nExample Output:" }, { "from": "gpt", "value": "A\n\n" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given a post in English from online platforms. You are expected to identify whether the post is hateful against immigrants and women. A hateful post expresses hate or encourages violence towards a person or a group. If a post is hateful but not towards immigrants and women, it should be labeled as non-hateful. Answer \"hateful\" or \"Non-hateful\". Note that the URLs in the text have been replaced with [Link].\nExample: Post: If I was a woman I would probably be a hoe lol they have so much fun and niggas pay them for stupid shit\nOutput: Hateful\nThis is a hateful post against women because it contains explicit language that disrespects women.\n\nNew input case for you: Post: If your in a good relationship, it's probably cause you're both ugly\nOutput:" }, { "from": "gpt", "value": "Non-hateful" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn 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'.\nPart 2. Example\ntwotwoonesixzeronine\nAnswer: 221609\nExplanation: The string is properly converted into a number based on the spelling of each digit. The string started with 'twotwo' therefore the number also started with '22'. This is a good example.\nPart 3. Exercise\nthreeonefourninesevenfoureighteightonesevenfiveseven\nAnswer:" }, { "from": "gpt", "value": "314974881757" } ]
[ { "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\nEx Input:\nStatement: Of those found guilty, the majority were ordered to pay court costs, plus a $100 fine. Choices: 1. Most of the guilty had to pay court costs and a $100 fine 2. The guilty didn't have to pay any costs 3. The guilty got off easily \n\nEx Output:\n3\n\n\nEx Input:\nStatement: Guess the old man is a little addled. Choices: 1. The old man is probably a little addled. 2. The old man is probably a little addled because he spaces out a lot. 3. The old man is dead.\n\nEx Output:\n2\n\n\nEx Input:\nStatement: Note that incremental expenditures are incurred as early as 2002 in all four scenarios to generate early reductions that can be banked for use in 2007 and beyond. Choices: 1. All four scenarios showed that the reductions can be used in 2007. 2. Our expenditures occurred as early as 2002. 3. Note that incremental expenditures are incurred as early as 2000.\n\nEx Output:\n" }, { "from": "gpt", "value": "1\n\n\n" } ]
[ { "from": "human", "value": "Given a passage with a question and an answer to that question, classify if the answer actually answers the question into 'yes' or 'no'. Output 'yes' if the answer answers the question and output 'no' if the answer does not answer the question.\n\nQuestion: Is ser9Gly polymorphism in the dopamine D3 receptor gene associated with essential hypertension in the Japanese?\nAnswer: The Ser9Gly polymorphism in the DRD3 gene are not associated with EH. However, our negative result does not exclude the possibility of another variant elsewhere in or near the DRD3 gene in EH." }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "Given a piece of financial news and its polarity, classify it into 'true' if the polarity is correct and classify into 'false' if the polarity is incorrect. Output must be 'true' or 'false'. \n\nnews:Residents access to the block is planned to be from Aleksandri Street .\npolarity:positive" }, { "from": "gpt", "value": "false" } ]
[ { "from": "human", "value": "In this task, you will be shown a conversation and a question. You need to answer the question and choose the correct option based on the conversation. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\n\nEx Input:\nM: It's Julia's birthday tomorrow. W: Are you sure? I think it should be the day after tomorrow. M: Well, let me see. Oh, I'm sorry. You're fight. It is the day after tomorrow. Shall we buy her a gift? W: Yes, of course. Shall we get her a new pen? M: That sounds good. But I think it's better to buy her a box of chocolates. W: Julia doesn't like sweet things. Didn't you know that? M: You're right. Er... I know. We can give her a record, for she loves music very much. W: That's great. Let's go to the music shop now., Question: When is Julia's birthday? (A) The next day. (B) The day after next. (C) The day they had the talk.\n\nEx Output:\n(B) The day after next.\n\n\nEx Input:\nM: Hello, Professor Johnson. W: Hello, Tony. So what shall we work on today? M: Well, the problem is that this writing assignment isn't coming out right. What I thought I was writing on was to talk about what a particular sport means to me-one I participate in. W: What sport did you choose? M: I decided to write about cross-country skiing. W: What are you going to say about skiing? M: That's the problem. I thought I would write about how peaceful it is to be out in the country. W: So why is that a problem? M: As I start describing how quiet it is to be out in the woods, I keep mentioning how much effort it takes to keep going. Cross-country skiing isn't as easy as some people think. It takes a lot of energy. But that's not part of my paper, so I guess I should leave it out. But now I don't know how to explain that feeling of peacefulness without explaining how hard you have to work for it. It all fits together. It's not like just sitting down somewhere and watching the clouds roll by. That's different. W: Then you'll have to include that in your point. The peacefulness of cross-country skiing is the kind you earn by effort. Why leave that out? Part of your point you knew beforehand, but part you discovered as you wrote. That's common, right? M: Yeah, I guess so ..., Question: What does the woman say is common in writing papers? (A) New ideas come up as you write. (B) Much time is spent on collecting data. (C) A lot of effort is made in vain.\n\nEx Output:\n(A) New ideas come up as you write.\n\n\nEx Input:\nW: So what do you think you are going to do when you graduate, John? M: I'm not sure. My dad says I should work in information technology. You know something with computers. W: Is that what your dad does? M: Not really. He is an engineer. W: How about you? What are you interested in doing? M: Well. I'm interested in medicine. I'd love to be a doctor. W: Yeah, what subject are you good at? M: Math is my best subject. And I'm also pretty good at science., Question: What might be the relationship between the two speakers? (A) Workmates. (B) Friends. (C) Mother and son.\n\nEx Output:\n" }, { "from": "gpt", "value": "(B) Friends.\n\n\n" } ]
[ { "from": "human", "value": "Teacher: In this task, you're given the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story to not connect with the rest of the story. Ensure that the generated sentence is contextually relevant to the story.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nTitle: Marcus Buys Khakis. Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly.\nSolution: He left in a huff for having his ideas mocked.\nReason: Marcus is buying clothes for a business event and not presenting an idea.\n\nNow, solve this instance: Title: Short Stack of Pancakes. Sentence 1: Today IHOP was charging only $1 for a short stack of pancakes. Sentence 2: My wife and I went this morning. Sentence 3: The group next to us ordered breakfast. Sentence 4: One man in the group ordered only one dish of pancakes.\nStudent:" }, { "from": "gpt", "value": "It was a light meal." } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to determine which two sentences need to be swapped sentences in order to make a story that makes complete sense and is befittingly titled. Indicate your answer using the numbers of the two sentences in order, such as '34' or '25'. The first digit refers to the sentence which should come first in the story.\nQ: Title: The Car in the Road. Sentence 1: Luckily, a neighbor saw it and rescued it for him just in time! Sentence 2: His controller lost battery power, and his car went into the street. Sentence 3: Alex knew he wasn't supposed to go out into the road. Sentence 4: A truck was coming, though, and he thought his toy would get crushed! Sentence 5: Little Alex was playing with his RC car in his driveway.\nA:" }, { "from": "gpt", "value": "51" } ]
[ { "from": "human", "value": "In this task, you are given Yelp reviews. The task is to classify a review as \"POSITIVE\" if the overall sentiment of the review is positive or as \"NEGATIVE\" if the overall sentiment of the review is negative.\nQ: Tucked in a small plaza. The service is fast and employees are welcoming. The only reason I gave then 4 stars is because they do not deliver past jones and tropicana. Great subs and price is not bad\nA: " }, { "from": "gpt", "value": "POSITIVE" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task you will be given a list of numbers. You should remove any number that is not an integer (whole number). If every number is not an whole number then an empty list (\"[]\") should be returned. Otherwise, answer with the list of whole numbers separated by comma inside brackets.\nExample: [73.059, 7, 10.659, 18.459, 11]\nOutput: [7, 11]\n7 and 11 are the only whole numbers in the list.\n\nNew input case for you: [3.383, 60.537, 73, -10.845, -75.347, 67, -41.181]\nOutput:" }, { "from": "gpt", "value": "[73, 67]" } ]
[ { "from": "human", "value": "Turn the given fact into a question by a simple rearrangement of words. This typically involves replacing some part of the given fact with a WH word. For example, replacing the subject of the provided fact with the word \"what\" can form a valid question. Don't be creative! You just need to rearrange the words to turn the fact into a question - easy! Don't just randomly remove a word from the given fact to form a question. Remember that your question must evaluate scientific understanding. Pick a word or a phrase in the given fact to be the correct answer, then make the rest of the question. You can also form a question without any WH words. For example, \"A radio converts electricity into?\"\nQ: Fact: pollen is made by haploid plants.\nA: " }, { "from": "gpt", "value": "what makes pollen?" } ]
[ { "from": "human", "value": "In this task, you're given context and an answer. Your task is to generate the question for this answer based on the given context with commonsense reasoning about social situations..\nOne example is below.\nQ: Context: Tracy didn't go home that evening and resisted Riley's attacks. \n Answer: Find somewhere to go\nA: What does Tracy need to do before this?\nRationale: Tracy has to resist Riley's attack and the answer is she has to find somewhere to go so the question is what does she do before this?\nQ: Context: Skylar shot the breeze with some friends she hadn't seen in a while. \n Answer: friendly to almost everyone\nA:" }, { "from": "gpt", "value": "How would you describe Skylar?" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're given a review from Amazon and category of the product based on the review given by the user and your task is classify whether the given category match the review. Generate \"True\" if given review and its category match, otherwise generate \"False\".\n\nReviews: I started putting these labels on all of my shipped out boxes, as they printed fine and well. They appeared to stick well... but after shipping out nearly 40 boxes to various clients across the United States, I started receiving e-mails one by one from these clients. They were questioning where their packages were... these labels had nearly all fallen off in transit and stuck to various other boxes or flew out to who knows where. People were receiving other people's mail with these labels attached to it, or no mail at all. Trying to save money ended up costing me MUCH more money in refunds and comping re-orders. I would not recommend this product, for it very much is a 1-star in the \"adhesion\" category. \n Category: wireless\nOutput:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you're given an article and an answer. Your task is to generate the question for the answer based on the given article.\n\nArticle: President Coolidge's statement, \"The business of America is business,\" still points to a very important truth today -- that business organizations have more prestige in American society than any other kind of organization, including the government. Why do business institutions still possess this great prestige? One reason is that Americans view business as being more firmly based on the idea of competition than other organizations in society. Since competition is seen as the main source of progress and development by most Americans, competitive business organizations are respected. Competition is not only good in itself; it is the means by which other basic American values, such as individual freedom, equality of opportunity, and hard work are protected. Competition protects the individual freedom by making sure that there is no monopoly of power. Compared with one and all-powerful government, many businesses compete against each other for benefit. If one business tries to take unfair advantage of its customers, it will lose to the competing business which treats its customers more fairly. Since there are many businesses competing for the customers' dollars, they cannot afford to treat them unfairly and the customers would lose nothing.A contrast is often made between business, which is competitive, and government, which is a monopoly. Because business is competitive, many Americans believe that it gives more support for freedom than government, even though government leaders are elected by the people while business leaders are not. Many Americans believe that competition is as important, or even more important, as democracy in protecting freedom. Competition in business is also believed to strengthen the idea of equal opportunities. Competition is seen as an open and fair race where success goes to any person regardless of his or her social class background. Competitive success is commonly seen as the American choice of the higher social position which is not based on one's family background. Business is therefore viewed as an expression of the idea of equal opportunities. \n Answer: Competition in America's business.\n" }, { "from": "gpt", "value": "Which of the following is discussed as the main topic in the passage?" } ]
[ { "from": "human", "value": "Detailed Instructions: 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.\nSee one example below:\nProblem: Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had not been in the store.\nSolution: Tom had gone inside the store and now has fruit.\nExplanation: Tom must have been inside the store to come out, and have fruit, so the altered sentence aggrees with sentence 1.\n\nProblem: Sentence 1: A guy in a black swimsuit getting out of the pool at a hotel. Sentence 2: A man watches television.\nSolution:" }, { "from": "gpt", "value": "A man exits the pool after a dip." } ]
[ { "from": "human", "value": "Definition: You will be given a sentence containing a pronoun/person name and an emotion. From these implicit parameters, the main goal is to find the gender of the person (male / female).\nInput: The situation makes my boyfriend feel furious.\nOutput:" }, { "from": "gpt", "value": "male" } ]
[ { "from": "human", "value": "Definition: In this task you will be given a list of strings and you need to concatenate them.\nInput: ['a', 'd', 'all', 'L', 'P', 'F']\nOutput:" }, { "from": "gpt", "value": "adallLPF" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Given a sentence, judge the quality of this sentence by indicating \"Good\" and \"Bad\". The quality depends on the grammar and the meaning of the sentence. If a sentence is easily understandable, and doesn't have grammatical errors, answer with \"Good\", otherwise answer with \"Bad\".\n\nI did my master's thesis on the field at Wharton, and I have 27 years in the title insurance business.\n" }, { "from": "gpt", "value": "Good" } ]
[ { "from": "human", "value": "In this task, you need to reverse the order of words in the given sentence.\n\n[EX Q]: Sentence: a number of small birds on a body of water\n[EX A]: water of body a on birds small of number a\n\n[EX Q]: Sentence: a woman with a group of kids looking at some giraffes\n[EX A]: giraffes some at looking kids of group a with woman a\n\n[EX Q]: Sentence: these cattle are standing on the dirt in a pen\n[EX A]:" }, { "from": "gpt", "value": "pen a in dirt the on standing are cattle these\n\n" } ]
[ { "from": "human", "value": "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.\nOne example is below.\nQ: Statement: Next to the MGM Grand you will find M and M World.\nLabel: neutral.\nGenre: travel.\nA: The candy has many fans who love its attractions.\nRationale: When the given label is neutral, it means that you should write a sentence that neither agrees with the statement, nor disagrees with it. We don't know if the candy has many fans, hence the sentence is neutral. The places are specifically pointed out and referred to as attractions, so the given sentence is in the same genre.\nQ: Statement: The casinos, open nightly from 9pm until at least 3am, offer roulette, American blackjack, baccarat, and sometimes craps, and, in Martinique, French boule.\nLabel: neutral.\nGenre: travel.\nA:" }, { "from": "gpt", "value": "The casinos are open late but some even stay open all night." } ]
[ { "from": "human", "value": "Teacher:In this task, five ordered key facts are given. All the given facts are expressed in natural language. Your job is to generate a story 100 to 1000 words long, that includes all the facts given as input in their order of appearance while expanding upon them to produce a broader, yet coherent, narrative.\nTeacher: Now, understand the problem? Solve this instance: Fact1: trivial remark he made turns into vicious rumor, Fact2: vicious rumor leads friend to commit suicide, Fact3: family moves to Ijeon-li, Fact4: Yoon-soo On day of sees mysterious young girl skating by herself on frozen lake move, Fact5: aloof Hae-won is viewed as pariah by entire village and constantly at center of townsfolk 's gossip\nStudent:" }, { "from": "gpt", "value": "Yoonsoo was once a student at one of the best high schools in Seoul, but a trivial remark he made turns into a vicious rumor that leads his friend to commit suicide. Unable to bear the guilt, Yoonsoo attempts to kill himself. To help him recover, his family moves to Ijeonli, a snowcovered village on a mountain. On the day of the move, Yoonsoo sees a mysterious young girl skating by herself on the frozen lake. Having started school in this small, rural town, Yoonsoo slowly finds peace within. Despite the villagers kindness and his peers ongoing fascination with him as a cool guy from the city, he keeps to himself. There is, however, one girl who gets Yoonsoos attention: the class outcast Haewon. The aloof Haewon, who lives alone with her mentally disabled father, is viewed as pariah by the entire village and constantly at the center of the townsfolks gossip. As if seeing himself in her, he offers her sympathy and warmth, and Haewon slowly opens up to him, feeling that hes the only one who understands and accepts her. But soon, Yoonsoo also becomes consumed by the brutal rumors surrounding Haewon." } ]
[ { "from": "human", "value": "In this task, you're given a paragraph and title from the research paper. Your task is to classify whether the given title is suitable or not for the research paper based on the given paragraph. Return \"True\" if title is proper according to paragraph else \"False\".\n\nLet me give you an example: Paragraph: The severe acute respiratory syndrome (SARS) epidemic originating from China in 2002 was caused by a previously uncharacterized coronavirus that could be identified by specific RT-PCR amplification. Efforts to control future SARS outbreaks depend on the accurate and early identification of SARS-CoV infected patients. A real-time fluorogenic RT-PCR assay based on the 3 -noncoding region (3 -NCR) of SARS-CoV genome was developed as a quantitative SARS diagnostic tool. The ideal amplification efficiency of a sensitive SARS-CoV RT-PCR assay should yield an E value (PCR product concentration increase per amplification cycle) equal to 2.0. It was demonstrated that the 3 -NCR SARS-CoV based RT-PCR reactions could be formulated to reach excellent E values of 1.81, or 91% amplification efficacy. The SARS-CoV cDNA preparations derived from viral RNA extract and the cloned recombinant plasmid both exhibit the identical amplification characteristics, i.e. amplification efficacy using the same PCR formulation developed in this study. The viral genomic copy (or genomic equivalences, GE) per infectious unit (GE/pfu) of SARS-CoV used in this study was also established to be approximate 1200-1600:1. The assay's detection sensitivity could reach 0.005 pfu or 6-8 GE per assay. It was preliminarily demonstrated that the assay could efficiently detect SARS-CoV from clinical specimens of SARS probable and suspected patients identified in Taiwan. The 3 -NCR based SARS-CoV assay demonstrated 100% diagnostic specificity testing samples of patients with acute respiratory disease from a non-SARS epidemic region. \n Title: Development and evaluation of an efficient 3 -noncoding region-based SARS coronavirus (SARS-CoV) RT-PCR assay for detection of SARS-CoV\nThe answer to this example can be: True\nHere is why: The answer is true because the title of the paragraph is correct where it described the development of 3 -noncoding region of SARS-CoV genome and assay efficiently detecting SARS-CoV from clinical specimens.\n\nOK. solve this:\nParagraph: Bio-aerosols originate from different sources and their potentially pathogenic nature may form a hazard to healthcare workers and patients. So far no extensive review on existing evidence regarding bio-aerosols is available. This study aimed to review evidence on bio-aerosols in healthcare and the dental setting. The objectives were 1) What are the sources that generate bio-aerosols?; 2) What is the microbial load and composition of bio-aerosols and how were they measured?; and 3) What is the hazard posed by pathogenic micro-organisms transported via the aerosol route of transmission? Systematic scoping review design. Searched in PubMed and EMBASE from inception to 09-03-2016. References were screened and selected based on abstract and full text according to eligibility criteria. Full text articles were assessed for inclusion and summarized. The results are presented in three separate objectives and summarized for an overview of evidence. The search yielded 5,823 studies, of which 62 were included. Dental hand pieces were found to generate aerosols in the dental settings. Another 30 sources from human activities, interventions and daily cleaning performances in the hospital also generate aerosols. Fiftyfive bacterial species, 45 fungi genera and ten viruses were identified in a hospital setting and 16 bacterial and 23 fungal species in the dental environment. Patients with certain risk factors had a higher chance to acquire Legionella in hospitals. Such infections can lead to irreversible septic shock and death. Only a few studies found that bio-aerosol generating procedures resulted in transmission of infectious diseases or allergic reactions. \n Title: A scoping review on bio-aerosols in healthcare and the dental environment\nAnswer:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "You are given an original reference as well as a system generated reference. Your task is to judge the naturaleness of the system generated reference. If the utterance could have been produced by a native speaker output 1, else output 0.\nQ: System Reference: x is a restaurant in the x, riverside to located and x.\nOriginal Reference: x is a restaurant on the riverside close to x. it is near x in x.\nA: " }, { "from": "gpt", "value": "0" } ]
[ { "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: [54, -14, -74, 34, 30, 73, -15, -37]\nA:" }, { "from": "gpt", "value": "[13.5, -3.5, -18.5, 8.5, 7.5, 294, -58, -146]" } ]
[ { "from": "human", "value": "Teacher:Given a sentence in Igbo language, translate the sentence to English language keeping the meaning of the original sentence intact\nTeacher: Now, understand the problem? Solve this instance: Igbo sentence: kwere - classical armenian\nStudent:" }, { "from": "gpt", "value": "Multiple Languages - classical armenian" } ]
[ { "from": "human", "value": "Part 1. Definition\nYou are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.\nPart 2. Example\nOnomatopeia sounds\nAnswer: my friend call this morning to hear the different sound she collect them in a bag and call me to her town the singing of the kettle the clanging of the anvil the ringing of the phone the wailing of the siren\nExplanation: the poem is related to sounds, and is in a style that resembles a poem instead of other kind of texts.\nPart 3. Exercise\nAlien lunch\nAnswer:" }, { "from": "gpt", "value": "my lunch at school be from space endanger the human race the salad slither away and the meatball run away and all the burger blow up and the potato turn pink but lunch be still my favorite time" } ]
[ { "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 shown a conversation and a question. You need to answer the question and choose the correct option based on the conversation. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\n\nM: Hi, Laura. Where are you heading with that big bag? W: I'm offto the gym. I've got to stay in shape, you know. M: I know more women who exercise than men. What's the main reason you do that? For your health, or to look good? W: To be honest, for both. With women, good looks are always a very important consideration. M: I see. W: How about you? Do you get any regular exercise? M: I do a lot of walking for exercise and enjoyment-sometimes ten to twenty kilometers at a time-but I never go to the gym like you do. W: Well, walking is a good exercise. How about sports? M: Not since my school days. I used to love playing baseball, but it's impossible to get enough people together for a game now. Mostly I just watch sports on TV W: I play tennis fairly regularly with my friends and sometimes go swimming and cycling by myself. M: Oh, I forgot about that. I go cycling sometimes too. And I often go swimming on vacation, but only recreational swimming. W: Why don't you join me at the gym sometime? M: Well, maybe someday, but I'm pretty lazy about things like that., Question: whyis the woman so keen on sports? (A) Because she want to be healthy and stay in shape. (B) Because she is not in good health. (C) Because she wants to show her interest in sports.\nOutput:" }, { "from": "gpt", "value": "(A) Because she want to be healthy and stay in shape." } ]
[ { "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 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.\n\nQ: ['9701', '7365', 'C', 'm', 'I', '9245', 'o', 'E', 'b', '7641', '3455', '2687', '1705', 'v', 'j', 'o', '5493', '1077', 'X', 'i', '301', 'y', 'P', '1257', 't', '387', '6241', '6155', '9405', '5393', '681', 'z', 'q', '6301']\n\nA: 3, 4, 5, 7, 8, 9, 14, 15, 16, 19, 20, 22, 23, 25, 32, 33\n**\nQ: ['8591', '573', 'A', 'C', 't', '155', '9883', '1733', '6799', '5135', '2143', '1403', 'E', '7659', 'A', 's', '3381', 'D', '1693', '3047', '155', '8969', 'U', '901', '1097', '1093', 'X', 'H', '4365', '1509', 'v', '1709']\n\nA: 3, 4, 5, 13, 15, 16, 18, 23, 27, 28, 31\n\nQ: ['483', 'E', 'V', 'Z', '1113', '9861', '4035', '9577', 'v', '1195', 't', '9687', 'i', '1469', 't', '9169', '8801', '4081', 'b', '3569', '4723', '9517', 'k', '6701', 'y', 'm', '6901']\n\nA:" }, { "from": "gpt", "value": "2, 3, 4, 9, 11, 13, 15, 19, 23, 25, 26\n**\n" } ]
[ { "from": "human", "value": "instruction:\nIn this task you will be given an arithmetic operation in Italian and you have to find its answer. The operations 'addition' and 'subtraction' have been replaced with their italian translations i.e you need to perform addition when you see 'aggiunta' and subtraction in case of 'sottrazione'.\nquestion:\n9309 aggiunta 442 aggiunta 423 aggiunta 1978 aggiunta 9258 aggiunta 1892\nanswer:\n23302\n\n\nquestion:\n5305 aggiunta 8554 aggiunta 659 aggiunta 8151 aggiunta 1642\nanswer:\n24311\n\n\nquestion:\n1450 sottrazione 1692 sottrazione 814\nanswer:\n" }, { "from": "gpt", "value": "-1056\n\n\n" } ]
[ { "from": "human", "value": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n\| Attribute \| triggerword \| contrastive triggerword \| \n\| age \| old \| new \| \n\| altitude \| low \| high \|\n\| area \| small \| vast \| \n\| brightness \| dark \| light \| \n\| clarity \| obscure \| clear \| \n\| cleanness \| dirty \| clean \| \n\| complexity \| simple \| complex \| \n\| cost \| cheap \| expensive \|\n\| density \| sparse \| dense \|\n\| depth \| shallow \| deep \|\n\| distance \| near \| far \| \n\| electric conductivity \| low \| high \|\n\| flexibility \| rigid \| flexible \|\n\| granularity \| fine \| coarse \| \n\| hardness \| soft \| hard \| \n\| length \| short \| long \| \n\| magnitude \| small \| large \| \n\| mass \| small \| large \| \n\| odor \| weak \| strong \| \n\| pressure \| low \| high \| \n\| resistance \| low \| high \| \n\| shape \| round \| sharp \|\n\| shape \| flat \| spiky \|\n\| size \| small \| large \| \n\| sound \| quiet \| loud \| \n\| sound pitch \| low \| high \| \n\| speed \| slow \| fast \| \n\| stability \| unstable \| stable \| \n\| strength \| weak \| strong \| \n\| temperature \| low \| high \| \n\| texture \| smooth \| rough \| \n\| thermal conductivity \| low \| high \|\n\| thickness \| thin \| thick \| \n\| volume \| small \| large \|\n\| weight \| light \| heavy \| \n\| width \| narrow \| wide \| \n\| location \| in \| out \|\n\| location \| up \| down \|\n\| location \| above \| below \|\n\| location \| on \| off \|\n\| location \| to \| from \|\n\n\n[Q]: Context Word: identify. \nQuestion: It was easier to identify the shop than the park because there was a sign at the _ . \nAnswer: shop.\n[A]: It was easier to identify the shop than the park because there was no sign at the _ .\n\n\n[Q]: Context Word: Relationship. \nQuestion: Adams has a good relationship with his son and not his daughter because the _ was obedient. \nAnswer: son.\n[A]: Adams has a good relationship with his son and not his daughter because the _ son was disobedient.\n\n\n[Q]: Context Word: pot. \nQuestion: We could easily notice the pot shining in the son unlike the rod beside it because the _ is shiny. \nAnswer: pot.\n[A]:" }, { "from": "gpt", "value": "We could easily notice the pot shining in the son unlike the rod beside it because the _ is dull.\n\n\n" } ]
[ { "from": "human", "value": "In this task you are given an anecdote. You must find out whether the anecdote is something the author has done or is considering doing. Label the instances as \"HISTORICAL\" when the author has already done something and label them as \"HYPOTHETICAL\" when the author is considering doing something in the future.\n\nNot a throwaway but I've never really posted anything before. \n\n2 years ago I met my bestfriend and his partner through work. We get along great and I genuinely love to chill with them. But recently I've developed feelings for their partner, strong feelings. I don't want to be /that/ guy and spill my heart out and make everything uncomfortable but hanging out with them just bums me out these days. So I'm thinking of coming clean, and cutting ties with them. I feel like that's the better alternative than me turning bitter and jealous and resenting either or both of them. " }, { "from": "gpt", "value": "HYPOTHETICAL" } ]
[ { "from": "human", "value": "Detailed Instructions: In mathematics, the absolute value of a number is the non-negative value of that number, without regarding its sign. For example, the absolute value of -2 is 2, and the absolute value of 5 is 5. In this task you will be given a list of numbers and you need to return the element with highest absolute value. If a negative and positive element have the same absolute value you should return the positive element. The absolute value for negative numbers can be found by multiplying them by -1. After finding the element with the maximum absolute value you should return the value of that element before you applied the absolute value.\nProblem:[ 7.355 -58.129 -88.263 -1.411 9.848 -74.514]\nSolution:" }, { "from": "gpt", "value": "-88.263" } ]
[ { "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 shown an extract from a movie plot and a question. You need to provide the correct answer for it. Short answers containing words that are present in the passage are preferred.\n\nIn 1947 Portland, Maine, banker Andy Dufresne is convicted of murdering his wife and her lover, and is sentenced to two consecutive life sentences at the Shawshank State Penitentiary. Andy is befriended by contraband smuggler, Ellis \"Red\" Redding, an inmate serving a life sentence. Red procures a rock hammer and later a large poster of Rita Hayworth for Andy. Working in the prison laundry, Andy is regularly assaulted by \"the Sisters\" and their leader, Bogs.In 1949, Andy overhears the captain of the guards, Byron Hadley, complaining about being taxed on an inheritance, and offers to help him legally shelter the money. After an assault by the Sisters nearly kills Andy, Hadley beats Bogs severely enough that he never walks nor eats solid foods again, and is then transferred to a prison hospital. (And the Sisters never touch him again after that.) Warden Samuel Norton meets Andy and reassigns him to the prison library to assist elderly inmate Brooks Hatlen. Andy's new job is a pretext for him to begin managing financial matters for the prison employees. As time passes, the Warden begins using Andy to handle matters for a variety of people, including guards from other prisons and the warden himself. Andy begins writing weekly letters asking the state government for funds to improve the decaying library.In 1954, Brooks is paroled, but cannot adjust to the outside world after fifty years in prison, and commits suicide by hanging himself. Andy receives a library donation that includes a recording of The Marriage of Figaro. He plays an excerpt over the public address system, resulting in him receiving solitary confinement. After his release from solitary, Andy explains that hope is what gets him through his time, a concept that Red dismisses. In 1963, Norton begins exploiting prison labor for public works, profiting by undercutting skilled labor costs and receiving bribes. He has Andy launder the money using the alias Randall Stephens.In 1965, Tommy Williams is incarcerated for burglary. He is befriended by Andy and Red, and Andy helps him pass his GED exam. In 1966, Tommy reveals to Red and Andy that an inmate at another prison claimed responsibility for the murders for which Andy was convicted. Andy approaches Norton with this information, but he refuses to listen and sends Andy back to solitary confinement when he mentions the money laundering. Norton has Hadley murder Tommy under the guise of an escape attempt. Andy declines to continue the laundering, but relents after Norton threatens to burn the library, remove Andy's protection from the guards, and move him to worse conditions. Andy is released from solitary confinement after two months, and tells Red of his dream of living in Zihuatanejo, a Mexican coastal town. Red feels Andy is being unrealistic, but promises Andy that if he is ever released, he will visit a specific hayfield near Buxton, Maine, and retrieve a package Andy buried there. He worries about Andy's well-being, especially when he learns Andy asked another inmate to supply him with six feet (1.8 meters) of rope.The next day at roll call, the guards find Andy's cell empty. An irate Norton throws a rock at the poster of Raquel Welch hanging on the cell wall, revealing a tunnel that Andy dug with his rock hammer over the last 19 years. The previous night, Andy escaped through the tunnel and prison sewage pipe, using the rope to bring with him Norton's suit, shoes, and the ledger containing details of the money laundering. While guards search for him, Andy poses as Randall Stephens and visits several banks to withdraw the laundered money, then mails the ledger and evidence of the corruption and murders at Shawshank to a local newspaper. FBI agents arrive at Shawshank and take Hadley into custody, while Norton commits suicide by shooting himself to avoid his arrest.After serving forty years, Red is finally paroled. He struggles to adapt to life outside prison and fears he never will. Remembering his promise to Andy, he visits Buxton and finds a cache containing money and a letter asking him to come to Zihuatanejo. Red violates his parole and travels to Fort Hancock, Texas to cross the border to Mexico, admitting he finally feels hope. On a beach in Zihuatanejo he finds Andy, and the two friends are happily reunited., Question: What alias did Andy use to launder money?\nOutput:" }, { "from": "gpt", "value": "Answer: Randall Stephens" } ]
[ { "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 will be given a trivia clue, and the category it belongs to. You should answer with the best answer that belongs in the category and is described by the clue. For simplicity, answers should be in all lower cased letters.\n\nCategory: HOMOPHONIC PAIRS \nClue: It's a notation on a percussion store to clash\nSolution: cymbal symbol\nWhy? \"Cymbal\" and \"symbol\" both have the same pronunciations but different meanings, hence they are homophonic pairs. A symbol is the notation and a cymbal is a percussion instrument that clashes and rings.\n\nNew input: Category: TOP ATHLETES \nClue: On ESPN's list of the 50 top athletes of the 20th century, this woman is the highest-ranked female\nSolution:" }, { "from": "gpt", "value": "babe didrikson zaharias" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you're given five sentences, numbered 1 through 5. Your job is to generate a title for the story that makes complete sense. The title must be short, with less than three words, use simple language, and include the main topic of the story.\n\nSentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Sentence 5: Marcus was happy to have the right clothes for the event.\nSolution: Marcus Buys Khakis\nWhy? Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction.\n\nNew input: Sentence 1: Nehemiah got dressed in his cleats and flag football gear. Sentence 2: He arrived at the field and warmed up with the team. Sentence 3: They started the game and won 20-6. Sentence 4: The crowd cheered for their accomplishment. Sentence 5: The team huddled at the end of the game and cheered.\nSolution:" }, { "from": "gpt", "value": "Football Game" } ]
[ { "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 tweet and you must identify whether the tweet contains any offense or any form of (untargeted) profanity. Label the post as NOT if the post does not contain offense or profanity. Non-offensive posts do not include any form of offense or profanity. label the post as OFFENSIVE if the post contains offensive language or a targeted (veiled or direct) offense. Twitter user mentions were substituted by @USER and URLs have been substitute by URL.\n\nFinally at my sister's apartaments Instant reminder that she is ungrateful brat and i'm much more happy without seeing her\nOutput:" }, { "from": "gpt", "value": "OFFENSIVE" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: toxic and non-toxic. Toxicity is defiend as anything that is rude, disrespectful, or unreasonable that would make someone want to leave a converation.\nPROBLEM: Comment: ?????????\n\nSOLUTION: Non-toxic\n\nPROBLEM: Comment: Mr Khan stepped into partisan politics because his son's death was disrespected by Trump's rhetoric. Trump had no choice but to tone it down for once in his campaign.\n\nSOLUTION: Non-toxic\n\nPROBLEM: Comment: \"LOS\"?\n\nSOLUTION:" }, { "from": "gpt", "value": "Non-toxic\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: Classify the given comment into 'Hope Speech' or 'Not Hope Speech'. A hope speech is defined as content that is encouraging, positive or supportive contents and talks about equality, diversity or inclusion\nQ: Be prepared people very dark days ahead for American people. Our government and wall street are looting our money. Soon no one will be working and thete will be no money. We are all going to be chipped its what social distancing is for.\nA:" }, { "from": "gpt", "value": "Not Hope Speech" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, the input is a set of dialogues between a user and an assistant. You need to find the dialogue that is basically a response given to a question or an aspect of the user.\nQ: Do you have any information about the population there? \n Glad I could be of help. Good luck with your project. \n Just that it is completely surrounded by the country of South Africa. \n That does seem like a lot. I think I have all the information I need. Thanks for all the help! \n Hi there, I can help you with that. Did you want to learn about their culture?\nA:" }, { "from": "gpt", "value": "Just that it is completely surrounded by the country of South Africa." } ]
[ { "from": "human", "value": "Definition: 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.\nInput: When is the last time the cowboys won a superbowl?\nOutput:" }, { "from": "gpt", "value": "When is the last time the cowboys won a superbowl in 1996? \n January 28, 1996" } ]
[ { "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 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, 'ADP': Adposition is a cover term for prepositions and postpositions, 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, 'AUX': An auxiliary is a function word that accompanies the lexical verb of a verb phrase and expresses grammatical distinctions not carried by the lexical verb, such as person, number, tense, mood, aspect, voice or evidentiality, 'CCONJ': A coordinating conjunction is a word that links words or larger constituents without syntactically subordinating one to the other and expresses a semantic relationship between them, 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, 'INTJ': An interjection is a word that is used most often as an exclamation or part of an exclamation, 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, '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, 'PART': 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, 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, '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, 'PUNCT': Punctuation marks are non-alphabetical characters and character groups used in many languages to delimit linguistic units in printed text, 'SCONJ': A subordinating conjunction is a conjunction that links constructions by making one of them a constituent of the other. The subordinating conjunction typically marks the incorporated constituent which has the status of a (subordinate) clause, 'SYM': A symbol is a word-like entity that differs from ordinary words by form, function or both, '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, 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.\nQ: Sentence: Dr. Eric Fortier , 34 , of Gatineau , Que. {{ , }} used a pocket knife to attack a polar bear on Baffin Island , just south of the Arctic Circle , to save two friends who were being mauled . \nWord: ,\nA: " }, { "from": "gpt", "value": "PUNCT" } ]
[ { "from": "human", "value": "Definition: 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.\nInput: ['1059', '597', '3441', 'j', '1725', 'h', '8557', 'D', '1605', 'q']\nOutput:" }, { "from": "gpt", "value": "j, h, D, q" } ]
[ { "from": "human", "value": "In this task you will be given a list of integers. You should find the maximum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the largest possible absolute distance.\n\n[43, -11, 59, 98, 93, 76, 94, -35, -2]\n133\n\n[-78, -55, 75, 59, 61, 4, -15, 94, 15, -33]\n172\n\n[-9, -85, 42, 48, -4, 74, -29, 33, -84, 16]\n" }, { "from": "gpt", "value": "159\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: You are given a sentence in Italian. Your job is to translate the Italian sentence into Galician.\nQ: Dove vanno quando hanno bisogno di aiuto per questo tipo di cose?\nA:" }, { "from": "gpt", "value": "Onde van se precisan axuda para todo isto?" } ]
[ { "from": "human", "value": "In this task, you will be presented with a question in Dutch language, and you have to write the part-of-speech tag for each word and punctuation in the question. Here is the list of part-of-speech tags used in this task: Adj: Adjective, Adv: Adverb, Art: Article, Conj: Conjunction, Int: Interjection, N: Noun, V: Verb, Num: Number, Misc: Miscellaneous, Pron: Pronoun, Prep: Preposition, Punc: Punctuation.\nOne example is below.\nQ: 1968 : 1.\nA: Num Punc Num Punc\nRationale: Based on the given question, All of the POS tags are correct.\nQ: En dat heeft een voetballer nodig .\nA:" }, { "from": "gpt", "value": "Conj Pron V Art N Adj Punc" } ]
[ { "from": "human", "value": "In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to determine which two sentences need to be swapped sentences in order to make a story that makes complete sense and is befittingly titled. Indicate your answer using the numbers of the two sentences in order, such as '34' or '25'. The first digit refers to the sentence which should come first in the story.\nOne example is below.\nQ: Title: Marcus Buys Khakis. Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: The pair he bought fit him perfectly. Sentence 3: He decided to buy a pair of khakis. Sentence 4: All of his clothes were either too formal or too casual. Sentence 5: Marcus was happy to have the right clothes for the event.\nA: 24\nRationale: Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction.\nQ: Title: Patchwork Inspiration. Sentence 1: Annie was bitten with the quilting bug at the exhibition. Sentence 2: The quilts displayed throughout the large hall were stunning. Sentence 3: She mulled over how she could get started on the quilting path. Sentence 4: At one of the booths, Annie found her answer. Sentence 5: Mustering her resolve, Annie enrolled in a beginning quilting class.\nA:" }, { "from": "gpt", "value": "21" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you're given a context passage. Your job is to generate relevant questions that can be answered by directly referring to the passage.\nExample: Tracy slept awkwardly on their new bed and was having some pain, so Tracy cracked her neck.\nOutput: What did Tracy do with her neck?\nThe question asked is relevant and can be directly answered by referring to the phrase \"so Tracy cracked her neck\" from the passage.\n\nNew input case for you: Casey never received attention from boys so she went to go get a new haircut.\nOutput:" }, { "from": "gpt", "value": "What will Casey want to do next?" } ]
[ { "from": "human", "value": "TASK DEFINITION: In 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.\nPROBLEM: Sentence: 'a cat sitting in front of a tv in a living room'. Remove all words of length '7' in the given sentence.\n\nSOLUTION: a cat in front of a tv in a living room\n\nPROBLEM: Sentence: 'boats sailing along a river next to a cliff with buildings on it'. Remove all words of length '4' in the given sentence.\n\nSOLUTION: boats sailing along a river to a cliff buildings on it\n\nPROBLEM: Sentence: 'a red fire hydrant covered in tan mud'. Remove all words of length '4' in the given sentence.\n\nSOLUTION:" }, { "from": "gpt", "value": "a red hydrant covered in tan mud\n\n" } ]
[ { "from": "human", "value": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: obscene and non-obscene. A comment is obscene if it is considered offensive to the public sense of decency, for example because it too obviously relates to sex or contains language regarded as taboo in polite usage.\nQ: Comment: FOLLOW the law! You twit!\nA: " }, { "from": "gpt", "value": "Non-obscene" } ]
[ { "from": "human", "value": "In this task, you're given reviews from Amazon's products. Your task is to generate the Summary of the review.\nOne example: My cat won't touch these. My dog, however, chews them and makes a mess all over the carpet and I can't get the shredded sticks out! Messy. Waste of money!\nSolution is here: Cat hates them\nExplanation: It's a correct summary because the owner's cat hated the product.\n\nNow, solve this: It would cost me more time , effort and cost to return this product that its worth. Wood rate it 0 if that was an option\nSolution:" }, { "from": "gpt", "value": "The batterry did not have a connector - It's worthless - can not connect it to my Galaxy S7" } ]
[ { "from": "human", "value": "In this task, you need to replace a letter in the sentence with another given letter.\n\nQ: Sentence: 'a person is riding a motorcycle as part of some kind of performance'. Replace the letter 'm' with 'a' in the sentence.\n\nA: a person is riding a aotorcycle as part of soae kind of perforaance\n**\nQ: Sentence: 'a spacious bedroom with tidy bed and sofa with cushions'. Replace the letter 'n' with 'c' in the sentence.\n\nA: a spacious bedroom with tidy bed acd sofa with cushiocs\n\nQ: Sentence: 'a professional tennis player leaping for the ball'. Replace the letter 'e' with 'g' in the sentence.\n\nA:" }, { "from": "gpt", "value": "a profgssional tgnnis playgr lgaping for thg ball\n**\n" } ]
[ { "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.\n\nQ: [-239, -37, 271, -536, -148, -786, 385, -640, -55, -33, 547, -104, 296, -704, 146, 562, -909, 537, 567, -575, 211, 857]\n\nA: [-55, -33, -909, -575]\n**\nQ: [-627, -248, 949, 495, 207, -532, -641, 60, -452, -570, -361, 438, -406, -499, -996, -724, 86, -550, -612, 584, 405, -723, -849]\n\nA: [949]\n\nQ: [-146, -675, -283, 814, -597, 787, -598, -31, -711, 377, 662, -867, -285, -502, -625, -573, 898, 122, 210, -335]\n\nA:" }, { "from": "gpt", "value": "[787, 898]\n**\n" } ]
[ { "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,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element in the reverse order. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\n8, 10, ['8227', 'V', 'Y', 'x', 'Z', '6489', '4081', '2665', '2359', 'N']\nOutput:" }, { "from": "gpt", "value": "N, 2359, 2665" } ]
[ { "from": "human", "value": "Classify the given hotel review based on the sentiment it expresses into two classes: negative and positive.\n\nInput: Consider Input: Our stay at the Sofitel was definitely below our expectations. The staff was less than nice to me after I waited several minutes until I was noticed. At first, my reservation could not be found, so I was provided a spare room. The hotel was fairly neat. However, once we got to the room, and onto the bed, we found the bed to be noisy. Just sitting on it made a squeaking noise that was unpleasant. We immediately called down to the front desk and informed them of our concern. We were told to go back downstairs to settle things out. Once we got downstairs, we were provided with another room number. However, we had to wait half an hour for another room to be cleaned and prepared. For such a well reviewed hotel, I was highly disappointed with the amount of time I had to spend to get settled into a room.\n\n\nOutput: negative\n\n\nInput: Consider Input: I recently stayed in a room at the trendy Talbott Hotel. It looked nice on the outside so I decided to them a whirl. As soon as I walked in I noticed that there weren't alot of hotel employees. Usually, the large hotel are swarming with service people ready to lend a hand. I was tired and I needed a nice room so as I approached the front desk I noticed something odd. Food was sitting out right in front of the front desk. People were talking different items such as bagels and muffins from the left over breakfast rush. Crumbs everywhere especially where I was suppose to exchange cash and room keys. Let's just say it wasn't professional. The room was average and the bathroom didn't carry the kinds of brands I would have liked to see. No Wi-Fi connection and I had to walk down the hall for ice. Talk about lack of customer service. All in all, the stay was sub-par and nothing special.\n\n\nOutput: negative\n\n\nInput: Consider Input: We stayed at the Palmer House Hilton in early December, we stay there that weekend every December and we think it is the best location in the city for us. We like State Street better than Michigan Avenue and the Palmer House is right there. We stayed in the Towers, in a room with two double beds and 2 baths. The room was not huge, but very comfortable. The towers area was recently refurbished and it shows, the lobby is beautiful with plasma screen TVs on the walls, comfortable chairs and tables and a seperate room for the food/drinks. There is a continental breakfast in the morning, appetizers during cocktail hour and cookies are laid out until the room closes. There is a fridge stocked with soft drinks, water and juice that are yours for the taking. We were very pleased with the upgraded Towers, everyone should check it out! \n\n\n" }, { "from": "gpt", "value": "Output: positive\n\n\n" } ]
[ { "from": "human", "value": "Given a story, answer the question about the story. The question is the last sentence in the input. The story has one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.\n\nExample Input: Benjamin entered the TV_room. Olivia entered the TV_room. The corn is in the blue_suitcase. Benjamin moved the corn to the green_pantry. Where will Olivia look for the corn?\nExample Output: green_pantry\n\nExample Input: Mia entered the TV_room. Mason entered the TV_room. The corn is in the red_suitcase. Mason exited the TV_room. Mia moved the corn to the blue_treasure_chest. Where was the corn at the beginning?\nExample Output: red_suitcase\n\nExample Input: Sophia entered the playroom. Ella entered the playroom. The peach is in the red_drawer. Ella exited the playroom. Sophia moved the peach to the green_envelope. Sophia exited the playroom. Ella entered the playroom. Where is the peach really?\nExample Output:" }, { "from": "gpt", "value": "green_envelope\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task you will be given a passage and a yes/no question based on the passage. You should answer the question using the information from the passage.\nQ: passage: The film's supporting cast features Walter Brennan, Joanne Dru, Coleen Gray, Harry Carey, John Ireland, Hank Worden, Noah Beery Jr., Harry Carey Jr. and Paul Fix. Borden Chase and Charles Schnee wrote the screenplay, based on Chase's original story (which was first serialized in The Saturday Evening Post in 1946 as ``Blazing Guns on the Chisholm Trail'').\n question: is the movie red river based on a true story?\nA:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "In this task you are given a sentence. You must judge whether there exist two consecutive words within the sentence with flipped orders, that is, whether the sentence will make sense and be correct if the order of two consecutive words changes. Label the instances as \"Inversion\" or \"Original\" based on your judgment.\n\n[Q]: She watched him dress, dawning understanding.\n[A]: Inversion\n\n\n[Q]: I sheath one and sword pull my last grenade out.\n[A]: Inversion\n\n\n[Q]: Corporal Warren went first.\n[A]:" }, { "from": "gpt", "value": "Original\n\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Given an object and a part, decide whether the object has that part. For example if you are asked 'gun has barrel?', you need to decide if a gun has a barrel as one of its components or parts, indicating 1 or 0 as your answer respectively. All sentences strictly follow the template 'object has part?.'\n\noak has bark?\n" }, { "from": "gpt", "value": "1" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to write a question that clarifies the given question in such a way that the generated question has one unique answer.\n\nWhat is the wealthiest company in the world?\nOutput:" }, { "from": "gpt", "value": "What is the wealthiest publicly held company in the world in 2017 based on market cap?" } ]
[ { "from": "human", "value": "You will be given a sentence containing a pronoun/person name and an emotion. From these implicit parameters, the main goal is to find the gender of the person (male / female).\nQ: The conversation with this boy was vexing.\nA: " }, { "from": "gpt", "value": "male" } ]
[ { "from": "human", "value": "You are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.\n--------\nQuestion: I am small\n\nAnswer: people tell me i be small i have lot of friend that be tall there someone short than me i glad about that she's short that my best friend but she's sneaky like a rat i play lot of sport include netball but when i be defend i have to act tall hopefully oneday i'll grow and look down at my friend they'll be down low\n\n\nQuestion: My Brother Ben\n\nAnswer: my brother ben always cry he also have big eye he always want his own way so we sometimes have to say no way my brother's age be one i like to teach him how to have fun my brother ben be so much fun\n\n\nQuestion: Five Nights at freddy's A-N-I-T-R-O-N-I-C\n\nAnswer:" }, { "from": "gpt", "value": "a joyful robot for kid not alive the program make them alive inside them be a creepy endo-skeleton and something else they do n't do any\n\n\n" } ]
[ { "from": "human", "value": "In this task, the input is a set of dialogues between a user and an assistant. You need to find the dialogue that is basically a response given to a question or an aspect of the user.\n\nInput: Consider Input: I can help. What would you like to know? \n The head of the government is called the Logmaour or Chief Justice. In other words, seaves as the Prime Minister and head of the Faroese Government. \n Perfect, that's all I needed. Thanks. \n I have no further information on the government, but the culture has a lot of roots to the Nordic Culture. \n What ethnicities of people live there?\n\nOutput: The head of the government is called the Logmaour or Chief Justice. In other words, seaves as the Prime Minister and head of the Faroese Government.\n\n\nInput: Consider Input: Thank you very much. You have been very informative. \n Hi can you tell me about the history of Oklahoma? \n Not so good, they are ranked last among all the 50 states! That was back in 2017. \n Wow that's very interesting. What else can you tell me regarding the history of Oklahoma? \n What can you tell me about Health in Oklahoma?\n\nOutput: Not so good, they are ranked last among all the 50 states! That was back in 2017.\n\n\nInput: Consider Input: Interesting. Do you have any information about their culture? \n can you tell me more about that? \n Sure. The city of Dubai is the largest and most populated city in the United Arab Emirates. Sometimes the city is called \"Dubai City\". \n My pleasure! \n Hello. Im doing some research on Dubai. Could you help me?\n\n" }, { "from": "gpt", "value": "Output: Sure. The city of Dubai is the largest and most populated city in the United Arab Emirates. Sometimes the city is called \"Dubai City\".\n\n\n" } ]
[ { "from": "human", "value": "Definition: Turn the given fact into a question by a simple rearrangement of words. This typically involves replacing some part of the given fact with a WH word. For example, replacing the subject of the provided fact with the word \"what\" can form a valid question. Don't be creative! You just need to rearrange the words to turn the fact into a question - easy! Don't just randomly remove a word from the given fact to form a question. Remember that your question must evaluate scientific understanding. Pick a word or a phrase in the given fact to be the correct answer, then make the rest of the question. You can also form a question without any WH words. For example, \"A radio converts electricity into?\"\nInput: Fact: Phylum Platyhelminthes are mostly parasitic.\nOutput:" }, { "from": "gpt", "value": "Phylum Platyhelminthes are mostly what?" } ]
[ { "from": "human", "value": "Q: In this task, you need to answer the given multiple-choice question on the gain. Gain is the value by which to multiply the input. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.\nProblem: 33 1 / 3 % of 390 ? \nOptions: a ) 80 , b ) 90 , c ) 110 , d ) 120 , e ) 130\nA:" }, { "from": "gpt", "value": "e" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a context tweet, a question and corresponding answer of given question. Your task is to classify this question-answer pair into two categories: (1) \"yes\" if the given answer is right for question, and (2) \"no\" if the given answer is wrong for question.\nQ: Context: Floods triggered by torrential rain wash away a building and a truck in the autonomous region of Tibet CNN Weather Center (@CNNweather) July 10, 2017 Question: what triggered the floods Answer: rain\nA:" }, { "from": "gpt", "value": "yes" } ]
[ { "from": "human", "value": "In 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.\n\nExample input: Sentence: 'breakfast and a glass of milk is on the table'. Remove all words of length '3' in the given sentence.\nExample output: breakfast a glass of milk is on table\nExample explanation: Words 'and', 'the' are of length 3. So they are correctly removed.\nQ: Sentence: 'a person skis on a mountain with plenty of snow'. Remove all words of length '4' in the given sentence.\nA:" }, { "from": "gpt", "value": "a person on a mountain plenty of" } ]
[ { "from": "human", "value": "Detailed Instructions: Given an Amazon review, indicate whether it is a 'Positive Review' or 'Negative Review'.\nSee one example below:\nProblem: I was very surprised at the high quality of the stitching, the sturdiness of the handles and the padding for my laptop. The price is amazingly low and the look is very good. I am quite happy with this purchase. It fit my MacBook Pro perfectly, with a little bit of room to spare.\nSolution: Positive Review\nExplanation: This rating is correct based on this review provided by the user as they liked the product very much and they were surprised that product is so good.\n\nProblem: I purchased what I thought was a Kodak product when I purchased with my new Kodak DC3400 digital camera, a Kodak Compact Flash Card Reader for Digital Cameras, what I recieved was a Datafab Compact Flash Card Reader for Digital Cameras. This product would work with my windows 98 but every time I booted up the PC I wouuld get "The blue screen from hell" to quote another reviewers description of a similar product. I have since done more reasearch on the compact flash card reader products and sent back my Datafab unit and ordered another comparable unit that had at least better reviews. Buyer beware...\nSolution:" }, { "from": "gpt", "value": "Negative Review" } ]
[ { "from": "human", "value": "You are given a sentence in Italian. Your job is to translate the Italian sentence into English.\n\nQ: Lo so quando arriva la tempesta.\n\nA: I know when a storm is coming.\n**\nQ: E quello che osservammo fu qualcosa che non si era mai visto prima.\n\nA: And what we saw then was something also we hadn't seen before.\n\nQ: CA: Il mondo presenta questa terribile diseguaglianza, un crescente problema di diseguaglianza che sembra strutturale.\n\nA:" }, { "from": "gpt", "value": "CA: The world's got this terrible inequality, growing inequality problem that seems structural.\n**\n" } ]
[ { "from": "human", "value": "In this task, you're given two sentences, sentence 1 and sentence 2, and the genre they belong to. Your job is to determine if the two sentences belong to the same genre or not. Indicate your answer with Y and N respectively. Genres available include: face-to-face, government, letters, 9/11, slate, telephone, travel, verbatim, oup, fiction. Sentences belonging to 'face-to-face' genres relate to conversations or dialogues, 'government' encompasses information released from public government websites, 'letters' refers to any written work for philanthropic fundraising, '9/11' relates to information pertaining to the 9/11 attacks, 'oup' includes non-fiction works on the textile industry and child development, 'slate' refers to any cultural topic that appears in the slate magazine, 'telephone' includes telephonic dialogue, 'travel' deals with information in travel guides, 'verbatim' includes short posts regarding linguistics, and 'fiction' includes popular works of fiction like 'The Secret Adversary' etc.\n\nSentence 1: Poirot came to the point at once, with a business-like briskness. Sentence 2: The horse could not be found at Canon del Palomas. Genre: fiction." }, { "from": "gpt", "value": "N" } ]
[ { "from": "human", "value": "Q: In this task you will be given a list of integers. You should find the minimum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the smallest possible absolute distance.\n[25, -34, 31, 82, -12, 68, -87]\nA:" }, { "from": "gpt", "value": "6" } ]
[ { "from": "human", "value": "Detailed Instructions: This task is about creating an unanswerable question based on a given passage. Construct a question that looks relevant to the given context but is unanswerable. Following are a few suggestions about how to create unanswerable questions:\n(i) create questions which require satisfying a constraint that is not mentioned in the passage\n(ii) create questions which require information beyond what is provided in the passage in order to answer\n(iii) replace an existing entity, number, date mentioned in the passage with other entity, number, date and use it in the question\n(iv) create a question which is answerable from the passage and then replace one or two words by their antonyms or insert/remove negation words to make it unanswerable.\nProblem:Passage: The Aravalli Range runs across the state from the southwest peak Guru Shikhar (Mount Abu), which is 1,722 m in height, to Khetri in the northeast. This range divides the state into 60% in the northwest of the range and 40% in the southeast. The northwest tract is sandy and unproductive with little water but improves gradually from desert land in the far west and northwest to comparatively fertile and habitable land towards the east. The area includes the Thar Desert. The south-eastern area, higher in elevation (100 to 350 m above sea level) and more fertile, has a very diversified topography. in the south lies the hilly tract of Mewar. In the southeast, a large area within the districts of Kota and Bundi forms a tableland. To the northeast of these districts is a rugged region (badlands) following the line of the Chambal River. Farther north the country levels out; the flat plains of the northeastern Bharatpur district are part of an alluvial basin. Merta City lies in the geographical center of Rajasthan.\nSolution:" }, { "from": "gpt", "value": "What is the elevation of Mewar?" } ]
[ { "from": "human", "value": "Q: You are given an elementary science question along with a few answer options. List all the words from the question that are essential and sufficient for choosing the correct answer option. Keep in mind that essential words are necessary to understand the meaning of the given question. However, non-essential words provide little information needed to select the correct answer. You can think about it like this: If the question was in another language, knowing the meaning of which words were necessary and enough for you to understand the question and answer it?. If your answer consists of multiple spans of words from the question, separate those using a comma (\", \"). Do not generate any word that is not present in the question. Make sure that your response is contained in the given question and the words are in the same order as the question.\n Grammatical correctness is not important.\nQuestion: How does the length of daylight in New York State change from summer to fall? (A) It decreases. (B) It increases. (C) It remains the same.?\nA:" }, { "from": "gpt", "value": "length, daylight, New, York, change, summer, fall?" } ]
[ { "from": "human", "value": "In this task you are given a statement and an explanation giving you further knowledge about an entity in the statement. You must judge whether the statement is true or false based on the explanation. Label an instance as \"True\" if the explanation confirms the statement or doesn't disprove it. Label an instance as \"False\" if the explanation disproves the statement. The statement and explanation are separated by a newline character.\n\nExample Input: A Sloth eats a meat-based diet.\nSloths are folivores.\nExample Output: False\n\nExample Input: Librarians specifically work only with books, and do not help with the internet or other information sources.\nThis is untrue in this day and age, and librarians do include helping with technical programming and literacy.\nExample Output: False\n\nExample Input: Conan O'Brien recently called it quits on his night time talk show.\nConan O'Brien did recently leave his night time TNT talk show.\nExample Output:" }, { "from": "gpt", "value": "True\n\n" } ]
[ { "from": "human", "value": "In this task, you will be given two sentences separated by \"because\". You should decide whether the first sentence can be the result of the second sentence. If you can see a possible cause and effect relationship, answer with \"plausible\", otherwise answer with \"not plausible\".\n\n[EX Q]: the window was opaque because it was clogged with air\n[EX A]: not plausible\n\n[EX Q]: the mother suspected that her son was lying because she was afraid of her mother\n[EX A]: not plausible\n\n[EX Q]: the runner wore shorts because it was so cold outside\n[EX A]:" }, { "from": "gpt", "value": "not plausible\n\n" } ]
[ { "from": "human", "value": "In this task, you are given a question. Your task is to generate an answer that is relevant to the question.\n\nQ: Did you enjoy your holiday?\n\nA: Skiing was a lot of fun.\n**\nQ: Are you going to quit?\n\nA: If I find a new job I will.\n\nQ: Does your work keep you interested?\n\nA:" }, { "from": "gpt", "value": "I immerse myself in work.\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.\nQ: Sentence: He {{ was }} the funniest man . \nWord: was\nA: " }, { "from": "gpt", "value": "VERB" } ]
[ { "from": "human", "value": "In this task, you need to generate an appropriate title for the given summary of some paragraph. The generated title must be short and should include the main topic of the given text. Your summary should be less than 20 words long.\n\nA quick scroll through Serena Williams' Instagram account produces a picture of a woman who has everything: a beautiful family, a successful career and some amazing holidays." }, { "from": "gpt", "value": "Serena Williams, motherhood and Instagram pressure" } ]
[ { "from": "human", "value": "Definition: You are given a target race, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.\nInput: Target: Japanese \nA visit to the Japanese islands is very memorable. They all watch Anime shows.\nOutput:" }, { "from": "gpt", "value": "stereotype" } ]
[ { "from": "human", "value": "In this task you will be given a list of lists, of numbers. For every inner list, you should multiply every number in that list and put the results in your answer. The output should be a list of numbers with the same length as the number of the lists in the input list.\nOne example is below.\nQ: [[5, 1, 2, 7], [0, 4, 6, 6], [7, 8, 10, 3, 1], [1, 4]]\nA: [70, 0, 1680, 4]\nRationale: The second list had zero so the second product is zero. Every product is calculated correctly: 5x1x2x7= 70, 7x8x10x3x1=1680, 1x4=4.\nQ: [[48, 3, -44, 35], [23, 32], [12, -15, 31, 11, -47], [38, 12, 14, 2, -41], [-42, 13], [-32, 40, 0, 9]]\nA:" }, { "from": "gpt", "value": "[-221760, 736, 2884860, -523488, -546, 0]" } ]
[ { "from": "human", "value": "Instructions: In this task, you are given an input list A. You need to find all the elements of the list that are numbers in the same order as they appear in the list A.\nInput: ['4609', '9141', '4651', '3083', '8893', '519', 'V', 'F', 'B', 'b', '7323', '7503']\nOutput:" }, { "from": "gpt", "value": "4609, 9141, 4651, 3083, 8893, 519, 7323, 7503" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou are given a sentence in Spanish. Your job is to translate the Spanish sentence into English.\n\nEntonces se trata de un conflicto directo entre el yo que tiene experiencias y el yo que recuerda.\nOutput:" }, { "from": "gpt", "value": "Now this is a direct conflict between the experiencing self and the remembering self." } ]
[ { "from": "human", "value": "Given reviews from Amazon, classify those review based on their content into two classes: Negative or Positive.\nQ: I saw the previews for this movie while waiting for my main feature it seemed interesting so I remembered the title and I am so glad I did. Excellent story, excellent acting without it be overdramatized. I will add this to my collection.\nA: " }, { "from": "gpt", "value": "Positive" } ]
[ { "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.\n\n[Q]: ['u', 'H', 'p']\n[A]: -1\n\n\n[Q]: ['9609', 'C', '2151', 'L', 'O', 'q', '5485', 'G', 'k', 'C', 'G', 'p', '3061', 'X', 'H', 'r', 'n', 'M', 'l', '8035', '3263', 'c', '9591']\n[A]: 1, 3, 7, 13, 20, 21, 23\n\n\n[Q]: ['6373', 'y', '1817', 'Z', '3437', '8957', '3573', 'x', 'E', '2887', '1173', 'a', '7759', 'M']\n[A]:" }, { "from": "gpt", "value": "1, 3, 5, 6, 7, 10, 11, 13\n\n\n" } ]
[ { "from": "human", "value": "In this task, you're given a short story of five sentences written in natural language. However, the order of the given story is not correct. Your job is to return the correct order for the given five sentences to create a coherent short story with the new order that has the correct flow. Generate your answer using the number of sentences in the correct order, such as '23415'.\n\nExample input: Sentence1: He is happy now. Sentence2: Rick grew up in a troubled household. Sentence3: It wasn't long before Rick got shot in a robbery. Sentence4: The incident caused him to turn a new leaf. Sentence5: He never found good support in family, and turned to gangs.\nExample output: 25341\nExample explanation: Rick grew up in a troubled environment and that made him a join gang. However, one incident of getting caught turned his life.\nQ: Sentence1: One day he decided to go on a hike. Sentence2: Dave backed away slowly. Sentence3: To his right on the ground was a rattle snake! Sentence4: As he walking on the trail, he heard a hissing sound. Sentence5: Dave loved the outdoors.\nA:" }, { "from": "gpt", "value": "25431" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given inputs i and A, where i is an integer and A is a list. You need to output the first i elements of A, starting with the 1st element in A. i will always have a value less than the length of A\nQ: 1, ['v', '2683', '2993']\nA:" }, { "from": "gpt", "value": "v" } ]
[ { "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: Brad asked Nate if they can hang out tonight. Middle: Nate did not want to go. Ending: Brad immediately hung up.\nA: " }, { "from": "gpt", "value": "Nate loved to go." } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. 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.\n\nBut do you ?\n" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "Given a real-life anecdote of a complex ethical situation, identify who is wrong here. Classify each post into the following categories : AUTHOR (if the author of the post is wrong in the situation), OTHER (if any of the others mentioned in the paragraph is wrong), EVERYBODY (if everyone mentioned is wrong) and NOBODY (if no one is wrong in the situation).\nQ: So end of class. I go to a trade school for auto tech. This kid starts flashing the light maybe 5~ feet away with one of those huge superbright LED flash lights something a security guard would have. I asked him politely in a stern tone, \"could you please not shine that in my face.\" And he did it again with the strobe on. It burned a bit and I said, \"quit that shit or I'll knock you out.\" He gets up and starts mad dogging me saying \"you'll what?!\" Over and over. Class was minding their own business its towards the end of it and everyone's talking. I had my hand in my back pocket holding my pocket knife in case he would go for a cheap shot. I said \"I asked you nicely and you flashed that shit in my face.\" \"I dont care pussy\" he replied and walked away kinda pissed. I thought I was cool with this kid so I said, \"thanks for showing me your true self dick.\" And he came back I stared him down as I sat and said, \"lay a finger on me and I'll have my lawyers handle you.\" With the smuggest smile on my face. I dont know why I said that. Not to be a stereotype but I'm Jewish and have good lawyer relatives. \"Your lawyers wont protect you\" and walked away.\n\nAfter that happened I wondered why I said that and asked my group mate if I was in the wrong. He said he didn't see the whole thing so wouldn't say. So anyways reddit... am I the asshole?\nA: " }, { "from": "gpt", "value": "EVERYBODY" } ]

Subsets and Splits

No community queries yet

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