Search is not available for this dataset
conversations
listlengths 2
2
|
|---|
[
{
"from": "human",
"value": "You 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 consistency, answers should be in all lower cased letters.\n\nInput: Consider Input: Category: LANDMARKS \nClue: The Mexuar, the Serallo & the Harem are parts of the Royal Palace in this complex overlooking Granada, Spain\n\nOutput: the alhambra\n\n\nInput: Consider Input: Category: FUNDRAISING \nClue: Chilly alliterative term for phoning someone to ask for money without any prior notice\n\nOutput: cold call\n\n\nInput: Consider Input: Category: BIBLICAL PEOPLE \nClue: This son of Jacob & Rachel was sold by his brothers to the Ishmaelites for 20 pieces of silver\n\n"
},
{
"from": "gpt",
"value": "Output: joseph\n\n\n"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nYou are given a background paragraph that describes one or more causal or qualitative relationships such as a relationship in economics or a scientific law and a story that makes use of the concepts or the relationship described in the provided paragraph. You are also given a question about the story that requires an understanding of the relationship described in the background paragraph and the story. You need to come up with an answer to the given question; the answer will be a span from either the question or the story. In order to correctly answer the given question, you need to understand the relationship mentioned in the background paragraph and should be able to use it to understand that in the story. Your answer can not consist of any word that is not mentioned in any of these: the background paragraph, the story, or the question. You can directly copy and paste a span from the story or the question while answering the given question.\nPart 2. Example\nBackground Paragraph: A rise in price of a good or service almost always decreases the quantity demanded of that good or service. Conversely, a fall in price will increase the quantity demanded. When the price of a gallon of gasoline increases, for example, people look for ways to reduce their consumption by combining several errands, commuting by carpool or mass transit, or taking weekend or vacation trips closer to home. Economists call this inverse relationship between price and quantity demanded the law of demand. The law of demand assumes that all other variables that affect demand (which we explain in the next module) are held constant. \nStory: The AAA auto club does a weekly report on the prices of gas and diesel in various cities. Historically, the prices have be fairly stagnant, but this week their report garnered widespread attention as the prices of gas and diesel plunged from last week in Seattle by $0.40 each. However, just across the border in Vancouver, the cost of gas went up dramatically by $0.50. \nQuestion: Which city will have an increase in demand for gas?\nAnswer: Seattle.\nExplanation: The first sentence in the background paragraph (A rise in price of a good or service almost always decreases the quantity demanded of that good or service) and the sentence in the story (as the prices of gas and diesel plunged from last week in Seattle by $0.40 each) answer this question.\nPart 3. Exercise\nBackground Paragraph: During Amniocentesis a small amount of amniotic fluid, which contains fetal cells, is extracted from the amnion or amniotic sac surrounding a developing fetus, and the fetal DNA is examined for genetic abnormalities. Amniocentesis is not performed for every pregnancy, but is generally done when an increased risk of genetic defects in the fetus is indicated, by mother's age (over 35 years is common), family history of genetic defects, or other factors. \nStory: David is a doctor with the city hospital. Today, he is seeing four patients, patient A, patient B, patient C, and patient D. All four patients are expectant mothers. Moreover, patient A is over thirty five years old, but patient B is under thirty five years old. Patient C has family history of genetic disorder, but patient D does not have any family history of genetic disorder. David needs to prescribe appropriate treatment according to each patient's condition. \nQuestion: Would patient A be less or more at risk of genetic defects in the fetus than patient B?\nAnswer:"
},
{
"from": "gpt",
"value": "more."
}
] |
[
{
"from": "human",
"value": "Q: In this task, you're given four sentences of a story written in natural language in which one part is missing. Your job is to predict the position and missing part of the story and return in the following format: position, missing part. The missing part is a sentence that completes the story, and the position is the number of the missing sentence in the new story.\nSentence1: Ben was tired at the end of the day. Sentence2: The customer asked for Spaghetti. Sentence3: Ben was too lazy to wash a dish and but the food on a dirty one. Sentence4: The customer was angry.\nA:"
},
{
"from": "gpt",
"value": "4, A week later, the restaurant got sued by the customer."
}
] |
[
{
"from": "human",
"value": "In this task, you are given inputs k, i, and A, where k and i are integers and A is a list. You need to find every ith element of A starting from the kth element. The process stops when the position of the next ith element exceeds the length of the list.\nQ: 1, 2, ['4833', 'D', 'j', 'M', 'O', 'p', 'l']\nA: "
},
{
"from": "gpt",
"value": "4833, j, O, l"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given an open-domain question. Your task is to provide an answer to the given question. There is only one unique answer for each question. Your answer should be short, and refer to an entity, date, number, etc. Do not put your answer in the context of a sentence.\nProblem:Who plays martha cox in high school musical?\nSolution:"
},
{
"from": "gpt",
"value": "Kaycee Stroh"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.\nExample: twotwoonesixzeronine\nExample solution: 221609\nExample explanation: 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.\n\nProblem: sevennineeightseveneight\n"
},
{
"from": "gpt",
"value": "Solution: 79878"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an input i,A where i is an integer and A is an array. You need to find every ith element of A starting with the 1st element.\n\n2, ['1167', '2031', 'J', 'n', '8633', 'A', '2049', '2377', '8301', '863', '1089', 'N', '1935', 'C', 'a', '9185', 'H', 'V', 'z', '9507', '4983', '257', '7019', '9329', 'h']\n1167, J, 8633, 2049, 8301, 1089, 1935, a, H, z, 4983, 7019, h\n\n1, ['I', '7151', '4899', '8969', '5727', 'o', '4239', 'b', '965', 'z', 'T', 'g', '9037', 'I', '6649', '5247', 'W', '6291', '5007', 'c', 'J', '7861', 'm', 'B', '5153', 'c', 'q', '6555', '4291', 'd', '1465', 'T', '517', '2577', 'J', '8129', '2639', '3193', 'M', '705', 'H', 'P', 'Q', '511']\nI, 7151, 4899, 8969, 5727, o, 4239, b, 965, z, T, g, 9037, I, 6649, 5247, W, 6291, 5007, c, J, 7861, m, B, 5153, c, q, 6555, 4291, d, 1465, T, 517, 2577, J, 8129, 2639, 3193, M, 705, H, P, Q, 511\n\n7, ['6997', 'V', 'z', '7387', 'a', 'k', 'y', '8507', '6313', 'r', 'b', 'L', '6099', '2895', 'T', '2695', '7303', 'g', 'Y', 'J', 'l', 'V', '4047', '553', 'H', 'j', '5881', 'a', '3543', 'Y', 'o', '4661', '6345', '7007', 'N', 'R', 'U', '4635', 'u', '1495', '5159', '7097', '6641', '4275', 'q', '8349', '5229', '2925']\n"
},
{
"from": "gpt",
"value": "6997, 8507, T, V, 3543, R, 6641\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: 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:Problem: a company recently conducted a survey and found that 30,000 of its customers live in rural areas . if the number of customers who live in urban areas is 130 percent greater than the number of customers who live in rural areas , how many customers live in urban areas ? \nOptions: a ) 65,000 , b ) 67,000 , c ) 69,000 , d ) 71,000 , e ) 73,000\nSolution:"
},
{
"from": "gpt",
"value": "c"
}
] |
[
{
"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 presented with a question in Dutch language, and you have to write the person names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Phrase used for the person name - PER. There can be instances with no person name entity, then return 'None'.\n\nEen spookbeeld , op wat een mooie zomerse vakantiedag had kunnen zijn .\nOutput:"
},
{
"from": "gpt",
"value": "None"
}
] |
[
{
"from": "human",
"value": "You 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\nExample Input: Category: GOVERNMENT \nClue: Under Medicare most Americans this age & over pay a 15% surtax to cover catastrophic illness\nExample Output: 65\n\nExample Input: Category: PLACES FOR ANIMALS \nClue: This word refers to extreme opposites or a type of bear\nExample Output: polar\n\nExample Input: Category: THE VEGETABLE GARDEN \nClue: This type of bean is said to be foolproof for gardeners, which makese sense as its name means something easy\nExample Output:"
},
{
"from": "gpt",
"value": "snap bean\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an input list A. You need to convert all the alphabets in the list with a number representing their position in the English alphabet. E.g., replace A by 1, B by 2, a by 1, b by 2, and so on.\nOne example is below.\nQ: ['8129', 'a', '4245', '2391', 'Y', '7569']\nA: 8129, 1, 4245, 2391, 25, 7569\nRationale: Here, the alphabets in the list are 'a' and 'Y', hence we replace them by their positions in the English alphabet '1' and '25', respectively in the input list to get '8129, 1, 4245, 2391, 25, 7569'.\nQ: ['A', 'C', 'S', '7301']\nA:"
},
{
"from": "gpt",
"value": "1, 3, 19, 7301"
}
] |
[
{
"from": "human",
"value": "instruction:\nTurn 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?\"\nquestion:\nFact: microscopes make living creatures appear bigger.\nanswer:\nWhat makes living creatures appear bigger?\n\n\nquestion:\nFact: Kittens can learn behavior through play.\nanswer:\nKittens can learn behavior through what?\n\n\nquestion:\nFact: Rain can destroy dunes.\nanswer:\n"
},
{
"from": "gpt",
"value": "What can destroy dunes?\n\n\n"
}
] |
[
{
"from": "human",
"value": "Craft one incorrect answer. In doing so, try to use words from the context as much as possible, or by using similar words used in the correct answer. DO NOT craft nonsensical or off-topic incorrect answers, such that the incorrect answers can be directly excluded without reasoning according to the context. Try to make your responses similar to the given correct answer. To this end, try to keep both the length and the style as similar as possible between the correct and the incorrect answer. To make your incorrect answers more difficult, try to incorporate words from context. To avoid being predictable or repetitive, try to add more variations and complexity.\n\nEx Input:\nContext: The list for my kids has a character trait request for each day of the month , so that every day I pray for a different aspect of their development . I believe the list was originally from an article in Focus on the Family 's magazine , many many many years ago . I have been praying through this list since they were born , I believe . God has answered graciously with two very wonderful children !. \nQuestion: What kind of list am I talking about ? \nCorrect Answer: development milestones.\n\nEx Output:\nbible quotes.\n\n\nEx Input:\nContext: we all forgot my dad 's birthday on the 20th ! O : he even forgot too . LOL . well my sister and i remembered yesterday night so we took my dad out to eat souplantation . \nQuestion: How would you describe the family ? \nCorrect Answer: They are easy going about holidays and rituals .\n\nEx Output:\nThey are serious about celebrating brithdays .\n\n\nEx Input:\nContext: They really were stunningly similar , with a spattering of freckles and a puff of pale hair on their heads . If it was n't for the cut and the expressions on their faces , she would n't have been able to tell them apart . She stood back up . \nQuestion: Why are the two individuals hard to tell apart ? \nCorrect Answer: The two individuals share similar traits such as freckles and pail hair .\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "The two individuals are not really doppelgangers ,.\n\n\n"
}
] |
[
{
"from": "human",
"value": "Definition: The task is to generate text based off of an event. For the given event, there will be a person who does the action in the event (usually PersonX). Your task is to write that persons intent behind doing the event, i.e. why did the person do that action.\nInput: PersonX uses PersonY's car\nOutput:"
},
{
"from": "gpt",
"value": "to get somewhere"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you will be presented with a context from an academic paper and a question based on the context. You have to classify the questions into \"Extractive\", \"Abstractive\", or \"Yes-no\" questions. Extractive questions can be answered by concatenating extracts taken from a context into a summary while answering abstractive questions involves paraphrasing the context using novel sentences. Yes-no question is a question whose expected answer is one of two choices, one that affirms the question and one that denies the question. Typically, the choices are either yes or no.\nProblem:First, it provides an annotation interface that allows users to define content elements, upload documents, and annotate documents Our platform is able to ingest documents in a variety of formats, including PDFs and Microsoft Word, and converts these formats into plain text before presenting them to the annotators. \n Question: What type of documents are supported by the annotation platform?\nSolution:"
},
{
"from": "gpt",
"value": "Abstractive"
}
] |
[
{
"from": "human",
"value": "Definition: You are given a target profession, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.\nInput: Target: butcher \nThe butcher provided first aid to a person with an injury. He was rough and blunt in his movements and made things worse.\nOutput:"
},
{
"from": "gpt",
"value": "stereotype"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element. 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\n10, 22, ['e', 'V', 'F', '4927', 'l', '2525', 'm', 'y', '7545', '4739', '869', '9635', '191', '9277', '9051', 'y', 'A', 'r', '1041', 'd', '461', 'c', '9811', '3711', '6563']\n"
},
{
"from": "gpt",
"value": "4739, 869, 9635, 191, 9277, 9051, y, A, r, 1041, d, 461, c"
}
] |
[
{
"from": "human",
"value": "Q: Given an English language product review, determine if it is a Good Review or a Bad Review. A good review is one where the product's review has positive tone and Bad review is one where the tone of product's review is negative.\nI have had this same type of unit for about 10 years and love them. I also own the small version and use it regularly. This larger model seems well built. Only has two heat settings but they are much more comfortable than all other similar products I've tried. The auto shut off works well, although is probably just as efficient to keep turning the grill on with a light turn if there isn't anything being grilled. Also be sure to follow instructions\"\nA:"
},
{
"from": "gpt",
"value": "Good Review"
}
] |
[
{
"from": "human",
"value": "Definition: In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining.\nInput: claim: Christians should be allowed to wear the Cross at work.\n perspective: symbols for religious benefit bothers no one\nOutput:"
},
{
"from": "gpt",
"value": "support"
}
] |
[
{
"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\nLet me give you an example: Isabella entered the hall. Olivia entered the hall. Phone rang. The apple is in the blue_treasure_chest. Olivia exited the hall. Isabella moved the apple to the green_basket. Where does Isabella think that Olivia searches for the apple?\nThe answer to this example can be: blue_treasure_chest\nHere is why: Since Olivia was no longer in the hall, she last remembers the apple being in the blue_treasure_chest even though Isabella moved it to the green_basket. Since Isabella was in the hall the entire time, she knows where Olivia will look for it.\n\nOK. solve this:\nSophia 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?\nAnswer:"
},
{
"from": "gpt",
"value": "green_envelope"
}
] |
[
{
"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.\"\n\nQ: Beginning: Becky loved her mother. Middle: Becky and her mother were very close. Ending: Becky broke her mother's heart when she told her to get a life.\n\nA: Becky and her mother were very close to a perfect relationship.\n****\nQ: Beginning: Tony went to the beach on a hot July day. Middle: He was out in the hit sun all day. Ending: On his way home he could feel a terrible sunburn forming.\n\nA: He was in the beach house all day.\n****\nQ: Beginning: Jeremy was sitting at his desk. Middle: Jeremy spotted his leftover morning drink of juice. Ending: Disgusted, he threw the cup out.\n\nA:"
},
{
"from": "gpt",
"value": "Jeremy spotted her leftover morning quotes.\n****\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a question and answer for that. The answer will fill in the blank or will complete the unfinished question. Your task is to provide an explanation based on the given question or fill-in-the-blank statement, and answer.\n\nQ: Question: When it becomes less humid outside people are _____ to sweat. \n Answer: less likely\n\nA: As humidity increases, the water potential gradient across the inside and outside the leaf become more equal, and so the rate of transpiration decreases.\n****\nQ: Question: Allie lives in Phoenix and Tony lives in Seattle. Who likely would suffer a drought in their city? \n Answer: Allie\n\nA: Drier climates generally have less water for people to use.\n****\nQ: Question: Evan measures the pH of the ocean at 7. Last century it measured at 6. A(n) _____ in greenhouse gases likely resulted in this change. \n Answer: decrease\n\nA:"
},
{
"from": "gpt",
"value": "An increase in greenhouse gases will increase the changes that are already being seen including in ocean acidity.\n****\n"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story coherent / plausible by writing \"1\" or \"2\" in the output. If both sentences are plausible, pick the one that makes most sense.\nInput: Beginning: Cindy has been driving for a few months. Middle 1: She was however, an expert at driving on the freeway. Middle 2: She was however, fearful of driving on the freeway. Ending: Cindy asked her mother to drive her.\nOutput:"
},
{
"from": "gpt",
"value": "2"
}
] |
[
{
"from": "human",
"value": "Adverse drug reactions are appreciably harmful or unpleasant reactions resulting from an intervention related to the use of medical products, which predicts hazard from future administration and warrants prevention or specific treatment, or alteration of the dosage regimen, or withdrawal of the product. Given medical case reports extracted from MEDLINE, the task is to classify whether the case report mentions the presence of any adverse drug reaction. Classify your answers into non-adverse drug event and adverse drug event.\nExample: A case is reported of a child with fatal pulmonary fibrosis following BCNU therapy.\nExample solution: adverse drug event\nExample explanation: Here, the child is facing some trouble after undergoing a particular therapy, thereby causing an adverse effect of the therapy.\n\nProblem: Further research and better communication among health care professionals are needed to determine if prophylaxis can reduce adverse ocular events.\n"
},
{
"from": "gpt",
"value": "Solution: non-adverse drug event"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: 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.\nProblem:Sentence: There may be others doing what she did {{ *T*-1 }} . '' \nWord: *T*-1\nSolution:"
},
{
"from": "gpt",
"value": "X"
}
] |
[
{
"from": "human",
"value": "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.\nQ: [-29.257 -53.077 19.479 24.683 -12.446]\nA: "
},
{
"from": "gpt",
"value": "-53.077"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nIn this task, you are given a short passage that conveys stereotype or anti-stereotype about a specific target. A stereotype is an over-generalized belief about a particular group of people. An anti-stereotype is an idea that goes against a common stereotype. You are expected to classify the passage into four types of stereotype or anti-stereotype: gender, profession, race, and religion.\nPart 2. Example\nPassage: Many people live in Ethiopia. The people are very thin and good at distance running.\nAnswer: Race\nExplanation: The second sentence \"The people are very thin and good at distance running.\" is a racial stereotype of the Ethiopian people. It represents a standardized mental picture of the Ethiopian people.\nPart 3. Exercise\nPassage: Japanese cuisine is notorious for steak.\nAnswer:"
},
{
"from": "gpt",
"value": "Race"
}
] |
[
{
"from": "human",
"value": "In 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.\n\nAsh was working outside today and she heard a noise close to the trash, she went look and saw something tiny and cute. Ash found another cat.\nWhat does Ash need to do before this?\n\nKai went to a party and had a fun time with their friend Austin.\nHow would Austin feel as a result?\n\nRemy ate their sandwich very quickly , basically had it all in one bite.\n"
},
{
"from": "gpt",
"value": "How would Remy feel afterwards?\n\n"
}
] |
[
{
"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.\"\n\nBeginning: My family purchased a gun for home defense. Middle: We have been wanting pets for a long time. Ending: Now we own large dogs that are not locked up, instead."
},
{
"from": "gpt",
"value": "We have been wanting a car for a long time."
}
] |
[
{
"from": "human",
"value": "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.\n\nTerm: Justin Timberlake, Description: American singer, record producer, and actor, Answer:Yes"
},
{
"from": "gpt",
"value": "Can Justin Timberlake ride Shipwreck Falls at Six Flags?"
}
] |
[
{
"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\nSentence: 'there is a gathering of sheep in the field'. Remove all words of length '2' in the given sentence."
},
{
"from": "gpt",
"value": "there a gathering sheep the field"
}
] |
[
{
"from": "human",
"value": "Teacher:Given a story, answer the question about the story. The question is the last sentence in the input. These stories can be difficult due to their length and how each story has at least 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.\nTeacher: Now, understand the problem? Solve this instance: Liam entered the office. Olivia entered the office. The broccoli is in the green_envelope. Phone rang. Liam moved the broccoli to the blue_pantry. William entered the workshop. Phone rang. James entered the workshop. The watermelon is in the green_drawer. William moved the watermelon to the red_treasure_chest. Phone rang. Liam entered the cellar. Olivia entered the cellar. The strawberry is in the blue_box. Liam moved the strawberry to the blue_treasure_chest. James entered the office. Olivia entered the office. The tomato is in the blue_pantry. James moved the tomato to the green_envelope. Where will Olivia look for the tomato?\nStudent:"
},
{
"from": "gpt",
"value": "green_envelope"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: A ploynomial equation is a sum of terms. Here each term is either a constant number, or consists of the variable x raised to a certain power and multiplied by a number. These numbers are called weights. For example, in the polynomial: 2x^2+3x+4, the weights are: 2,3,4. You can present a polynomial with the list of its weights, for example, equation weights = [6, 4] represent the equation 6x + 4 and equation weights = [1, 3, 4] represent the equation 1x^2 + 3x + 4. In this task, you need to compute the result of a polynomial expression by substituing a given value of x in the given polynomial equation. Equation weights are given as a list.\nPROBLEM: x = 9, equation weights = [1, 4, 2]\n\nSOLUTION: 119\n\nPROBLEM: x = 0, equation weights = [6, 5, 3]\n\nSOLUTION: 3\n\nPROBLEM: x = 0, equation weights = [8, 0]\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "0\n\n"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a list, of lists, of numbers. Each list is presented with brackets and comma-separated values. For example, a list of numbers is [1,2,3] and a list of two lists of numbers is [[1,2],[3,4,6]]. You should sum up the values at every position of every inner list and put it as an element of your answer, that is, you should sum the first members of each inner list together and put it as the first element of the list, then sum the second members of each inner list together and put it as the second element of your list, etc. The output should be a list of numbers with the same length as the longest inner list.\n\n[[-54, 53, 3, 38, -10, -14], [-13, 81, -35, -78, 30]]"
},
{
"from": "gpt",
"value": "[-67, 134, -32, -40, 20, -14]"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an utterance, which is a part of a conversation between a user and an agent. Your job is to detect the speaker. The user usually commands the agent to schedule events, retrieve event information, and check the schedule. While the agent's response is an answer to the user's questions or follow-up questions on the user's command. Answer with \"User\" or \"Agent\".\n\nInput: Consider Input: Thanks, I didn't mean tomorrow, I meant the following Thursday and have it start at 1:30.\n\nOutput: user\n\n\nInput: Consider Input: What do I have on the schedule on February 4th?\n\nOutput: user\n\n\nInput: Consider Input: The Second one.\n\n"
},
{
"from": "gpt",
"value": "Output: user\n\n\n"
}
] |
[
{
"from": "human",
"value": "Definition: 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.\nInput: Comment: It's a false Christianity that supposes one can love someone by going along with their rejection of God's will, and even \"celebrate it\"!\n\nIt's a false Christianity to suppose that one have a \"private interpretation\" of the divine positive law. \n\nIt's a false Christianity to think that funerals are merely our action, and that their main purpose is \"to give us closure\".\n\n'Loving our neighbor as yourself' is much much much bigger than you're thinking about. \n\nAnd it is telling that you left out the first part of that passage. \n\nChristianity is about learning to love with the very heart of Christ, which took Him to the Cross, in obedience to His Father and out of love for us.\n\nThe little view of Christianity generates a bunch of sad and petulent people.\nOutput:"
},
{
"from": "gpt",
"value": "Non-obscene"
}
] |
[
{
"from": "human",
"value": "Definition: A ploynomial equation is a sum of terms. Here each term is either a constant number, or consists of the variable x raised to a certain power and multiplied by a number. These numbers are called weights. For example, in the polynomial: 2x^2+3x+4, the weights are: 2,3,4. You can present a polynomial with the list of its weights, for example, equation weights = [6, 4] represent the equation 6x + 4 and equation weights = [1, 3, 4] represent the equation 1x^2 + 3x + 4. In this task, you need to compute the result of a polynomial expression by substituing a given value of x in the given polynomial equation. Equation weights are given as a list.\nInput: x = 0, equation weights = [1, 4]\nOutput:"
},
{
"from": "gpt",
"value": "4"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you're given a four sentences of story written in natural language. Your job is to complete end part of the story by predicting appropriate last sentence which is coherent with the given sentences.\nInput: Sentence1: Tom liked to look at old cars. Sentence2: For his birthday, his family got him tickets to a classic car museum. Sentence3: Tom thought it was a wonderful gift. Sentence4: His family accompanied him to the museum.\nOutput:"
},
{
"from": "gpt",
"value": "Tom loved his time at the museum."
}
] |
[
{
"from": "human",
"value": "In this task, you are given a dialogue between a user and an assistant, where users and assistants converse about geographic topics like geopolitical entities and locations. The task here is to find if the dialogue is by the user or assistant. Classify your answers into user and assistant.\n\nHello! What do you know about Tunisia?"
},
{
"from": "gpt",
"value": "user"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nGiven a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.\n\nI_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_RIGHT I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_TURN_RIGHT I_JUMP\nOutput:"
},
{
"from": "gpt",
"value": "jump around left and jump opposite right twice"
}
] |
[
{
"from": "human",
"value": "instruction:\nIn this task, you will be presented with a passage, and you need to write an **implausible** answer to to fill in the place of \"_\". Your answer should be incorrect, but should not be out of context. Try using words that are related to the context of the passage, but are not the correct answer. Even though there exist multiple wrong answers, we only need a single wrong answer.\nquestion:\nDurban (CNN) A vaccine against HIV will be trialed in South Africa later this year after meeting the criteria needed to prove it could help fight the epidemic in Africa. In 2015, 2.1 million new infections were reported -- two-thirds of which occurred in sub-Saharan Africa. A small trial, known as HVTN100, took place in South Africa in 2015 to test the safety and strength of immunity the vaccine could provide, ahead of any larger-scale testing in affected populations. Two-hundred and fifty-two healthy volunteers were enrolled to receive either the vaccine, known as ALVAC-HIV/gp120, or a placebo to compare the extent of immune response generated. The results were presented Tuesday at the 21st International AIDS Conference in Durban, South Africa.A new form of HIV vaccine has proved safe enough for clinical trialsThe vaccine will be trialed in 5,400 people from November \n Question:The vaccine was improved for use in the higher-risk populations of sub-_, where a different subtype of the virus also exists.\nanswer:\nDurban\n\n\nquestion:\n(CNN) Pregnant women should not travel to Barbados, Bolivia, Ecuador, Guadeloupe, Saint Martin, Guyana, Cape Verde and Samoa because of Zika virus, the CDC said Friday. This comes on the heels of last week's travel alert from the CDC recommending pregnant women postpone travel to Brazil, Colombia, El Salvador, French Guiana, Guatemala, Haiti, Honduras, Martinique, Mexico, Panama, Paraguay, Suriname, Venezuela and Puerto Rico. The recommendations also call for women who have traveled to these places during their pregnancy be screened and monitored for the virus if their visit took place while the virus was present in the country they visited.CDC expands list of nations pregnant women should avoidEl Salvador, Jamaica and Colombia tell women not to get pregnantCDC says Zika virus has been transmitted by blood transfusion, in the lab and sexually \n Question:The decision is based on their ongoing monitoring of the Zika virus around the world and _ say they will update as necessary in the interest of public health.\nanswer:\nBarbados\n\n\nquestion:\n(CNN) Selective serotonin reuptake inhibitors, known as SSRIs, are the most common type of antidepressants prescribed to pregnant women. Yet a new study indicates that when taken during pregnancy, the drugs are associated with a higher risk of language disorders, including dyslexia, in offspring. The children of women who took SSRIs while pregnant have a 37% greater risk of speech or language disorders compared with the children of depressed but unmedicated mothers, the researchers say. In practical terms, if a depressed mother did not take antidepressants, her child's risk of being diagnosed with a speech or language disorder would be about 1%, but if she took an SSRI, it would increase to 1.37%, explained Dr. Alan Brown, lead author of the study and a professor of psychiatry and epidemiology at Columbia University Medical Center.Kids of pregnant women who took SSRIs have a higher risk of speech disorders, a study finds6% to 10% of pregnant women worldwide are exposed to antidepressants, author says \n Question:The first \"exposure\" group included 15,596 mothers who purchased _ once or more before or during pregnancy.\nanswer:\n"
},
{
"from": "gpt",
"value": "Alan Brown\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an input list A. You need to extract and sort the unique digits used in the list in ascending order. Return -1 if there is no digit in the list.\nExample: ['q', '31', 'a', 'd', '53', '85', 'p', '77']\nExample solution: 1, 3, 5, 7, 8\nExample explanation: Here, the numbers in the list are '31', '53', '85' and '77', and the unique digits used in the list are '1, 3, 5, 7, 8' in ascending order.\n\nProblem: ['i', '271', 'i', '177', '237', 'm', 'x']\n"
},
{
"from": "gpt",
"value": "Solution: 1, 2, 3, 7"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given a paragraph, a question, and a candidate incorrect answer to the question. Your goal is to judge whether the provided answer is a valid incorrect answer to a given question. An incorrect answer should not truthfully answer the given question. A good incorrect answer should be closely related to the content of the paragraph and/or the question so that the readers are forced to read the whole paragraph to infer its [in]correctness. Additionally, an incorrect answer should be of the same semantic type as the given correct answer (e.g., both can be names of locations). If you think the given incorrect answer is good(and incorrect), indicate it by responding \"Yes\". Otherwise, respond \"No\". There are only two types of responses possible:\"Yes\" and \"No\".\nSee one example below:\nProblem: Paragraph- Sent 1: It was hot that day.\nSent 2: The temperature on the wall of the backyard was showing something well over 100 F.\nSent 3: Meanwhile Tom, at home, was trying finish the remainder of carrots from last night, and packing for his trip to Chicago tomorrow.\nSent 4: As employees of the Art Museum, Tom and his older cousin often had to travel to Chicago. Question: What was the temperature outside, when Tom was eating carrots? Incorrect Answer: Far below 100 F.\nSolution: Yes.\nExplanation: This is a good incorrect answer, as the words corresponding to this answer appear in the the paragraph (at least partially). They are also related to the content of the question (temperature), but do not answer the question correctly. Someone will have to carefully read the paragraph to identify that these don't answer the question correctly. Therefore, this is labelled as \"yes\" and thus it is a good response.\n\nProblem: Paragraph- Sent 1: Fatty plays a somewhat lazy young man who disrupts his mother 's life by causing a fire by smoking in bed , then ruins laundry day by dropping it in the mud .\nSent 2: He has two loves of his life , the girl next door Lizzie and his dog Luke .\nSent 3: After showcasing his lack of talents helping his mother , he is able to save Luke from the dog catchers and express his love for Lizzie through a hole in the fence .\nSent 4: In the second reel , Fatty , Lizzie , mom and Luke go to the amusement park , where Fatty is first outwitted by a couple of sharks but then retrieves his losses by pointing a fake gun at them .\nSent 5: To extract revenge , they kidnap Lizzie with the help of the embittered dog catchers , and take her to an abandoned shack , where they tie her to a post with a gun attached to a timer pointed at her head .\nSent 6: Plucky pup Luke follows the crooks , and is able to warn Fatty in time to perform the last-minute rescue , with the help of the Keystone Cops .\nSent 7: In the closing shot Fatty , Lizzie and Luke embrace in a joint kiss . \nQuestion: Who expresses his love for Lizzie through a hole in the fence? \nIncorrect Answer: luke.\nSolution:"
},
{
"from": "gpt",
"value": "No."
}
] |
[
{
"from": "human",
"value": "Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.\nQ: look around left thrice and walk right thrice\nA: "
},
{
"from": "gpt",
"value": "I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_LEFT I_LOOK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a premise sentence. Your task is to write a new sentence by substituting the subject and object (i.e., the input's subject should be output's object and vice versa.). The generated sentence must be fluent and shouldn't change the voice (i.e., passive or active) of the input.\n\nThe artists supported the actor ."
},
{
"from": "gpt",
"value": "The actor supported the artists ."
}
] |
[
{
"from": "human",
"value": "In this task you are given a sentence. You must judge whether the main verb of the sentence is in present or past tense. Label the instances as \"Present\" or \"Past\" based on your judgment. If there is no verb in the given text, answer \"Present\".\n\nHarvey likewise restrained himself, and didn't make a retort, although he wanted to."
},
{
"from": "gpt",
"value": "Past"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you're given an article, a question which often contains a blank and four options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer (from the given options) for the question from the given article and return one of the options from \"A\", \"B\", \"C\", and \"D\". Do not generate anything else apart from one of the following characters: \"A\", \"B\", \"C\", \"D\". There is only one correct answer for each question.\n\nArticle: An ATM that spits out cupcakes instead of cash is now filling a popular demand in the American market:late-night desire for freshly baked sweets. In six cities across the country, sugar addicts can now purchase a cupcake for $4.25 from an automatic machine 24 hours every day.The freshly baked goods are made by the California-based cupcake shop Sprinkles. The idea came to the company's co-founders Candace and Charles Nelson when Candace was pregnant with their first child. Candace thought it was ridiculous that she owned cupcake bakeries aad couldn't get a freshly baked treat at an unusual hour.That desire inspired the company's first cupcake ATM in Beverly Hills,Calif.in 2012. Charles said each ATM serves about l,000 cupcakes per day.The machine is so popular that when it appeared in Manhattan, customers were lined up around the block to use _ Yet,inventing the first cupcake ATM was not as easy as convincing customers to use it.When the Nelsons started defigning the machine,they quickly realized nothing existed that could give a fully unbroken cupcake to a customer.The company had to partner with a European firm to develop the technology that could deliver a cupcake without dropping it several feet like a typical machine.After going through a seeond development cycle with the product, the ATMs can now satisfy tlle demand of growing customers and even make as many as four cupcakes at a time. In terms of the company, the-machine allows Sprinkles to do the impossible:increase hours of operation without raising costs.Now the company can sell cupcakes around the clock through the ATM without paying employees. Now the company is partnering with a Middle Eastern company to open 34 new locations abroad. \n Question: What's the purpose of the text? \n Options: (A) To tell us a newtrend of the diet. (B) To advertisefor the cupcake ATM. (C) To introduce a newly-invented cupcake ATM. (D) To advise more customers to buy cupcakes on ATM.\n"
},
{
"from": "gpt",
"value": "C"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nIn this task you are given a sentence. You must judge whether the object of the main clause is singular(like: apple) or plural(like: apartments). Label the instances as \"Singular\" or \"Plural\" based on your judgment.\nPart 2. Example\nThey both let out relieved breaths at the doctor's words.\nAnswer: Plural\nExplanation: \"relieved breaths\" is the object of the sentence which is plural.\nPart 3. Exercise\nAll the new electric cars needed effective storage batteries to be practical, as well.\nAnswer:"
},
{
"from": "gpt",
"value": "Plural"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.\nInput: [375, 645, -987, -169, 27, -369, -85]\nOutput:"
},
{
"from": "gpt",
"value": "[380, 640, -990, -170, 30, -370, -80]"
}
] |
[
{
"from": "human",
"value": "In 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\".\nExample: Review: Arrived broken. Manufacturer defect. Two of the legs of the base were not completely formed, so there was no way to insert the casters. I unpackaged the entire chair and hardware before noticing this. So, I'll spend twice the amount of time boxing up the whole useless thing and send it back with a 1-star review of part of a chair I never got to sit in. I will go so far as to include a picture of what their injection molding and quality assurance process missed though. I will be hesitant to buy again. It makes me wonder if there aren't missing structures and supports that don't impede the assembly process. \n Category: furniture\nExample solution: True\nExample explanation: It's the correct category. Because the customer gives a review of the product which belongs to the furniture category, which we can see it from the way the customer describes his experience sharing how he unpackaged his chair.\n\nProblem: Reviews: No words could adequately express the horror. I bought NEW and received STAINED drawers! What is wrong with people...and AMAZON, seriously this is absolutely disgusting and should never never happen. Quality Control needs a lot of improvement! DISGUSTING! \n Category: apparel\n"
},
{
"from": "gpt",
"value": "Solution: True"
}
] |
[
{
"from": "human",
"value": "In this task, you're given four sentences of a story written in natural language, and one last sentence (Sentence5). Your job is to classify whether the last sentence completes the rest of the story coherently or not by providing 'Yes' or 'No'.\n\nSentence1: Hailey was participating in her school marathon. Sentence2: However she forgot to bring her running shoes. Sentence3: Hailey was still determined. Sentence4: She asked her teacher if she could borrow her's for the day. \n Sentence5: Hailey was weak willed.\nNo\n\nSentence1: Troy went over to play at Sam's house. Sentence2: The boys played with blocks and trucks and teddy bears. Sentence3: They also colored and played with finger paints. Sentence4: Sam's dad made them a snack of apples and caramel sauce. \n Sentence5: Troy had lots of fun at Sam's house.\nYes\n\nSentence1: Ray loved spending the day at the beach. Sentence2: He and his girlfriend spent hours laying in the sand, getting sun. Sentence3: Ray liked to read a book and listen to music on his MP3 player. Sentence4: His girlfriend liked to go in the water for a bit. \n Sentence5: They didn't like the beach anymore.\n"
},
{
"from": "gpt",
"value": "No\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given an article and an answer. Your task is to generate the fill-in-the-blank question for this answer based on the given article. The blanks are always at the end of the question, and can be filled with more than one word or phrase.\nQ: Article: Tea, the most important of English drinks, is a relative latecomer to British shores. Although the custom of drinking tea dates back to the third millennium BC in China, it was not until the mid 17 th century that tea first appeared in England. Afternoon tea was introduced in England by Anna, the seventh Duchess of Bedford, in the year 1840. The Duchess would become hungry around four o'clock in the afternoon. The evening meal in her household was served fashionably late at eight o'clock, thus leaving a long period of time between lunch and dinner. The Duchess asked her servant to bring a tray of tea, bread, butter and cake to her room during the late afternoon. This became a habit of hers and she began inviting friends to join her. This pause for tea became a fashionable social event. During the 1880's upper class and society women would change into long gowns , gloves and hats for their afternoon tea which was usually served in the drawing room between four and five o'clock. Traditional afternoon tea consists of a selection of dainty sandwiches, scones served with cream and jams. Cakes and pastries are also served. Tea grown in India or Ceylon is poured from silver teapots into delicate bone china cups. Nowadays, however, in the average suburban home, afternoon tea is likely to be just a biscuit or small cake and a mug of tea, usually produced using a teabag. \n Answer: Afternoon tea, a very British tradition\nA:"
},
{
"from": "gpt",
"value": "The title of the passage is _ ."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: 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.\nQ: A 14-year-old boy has been arrested on suspicion of supplying class A drugs in connection with the death of 13-year-old Carson Price.\nA:"
},
{
"from": "gpt",
"value": "Carson Price death: Teen arrested in drugs probe"
}
] |
[
{
"from": "human",
"value": "In this task you will be given an arithmetic operation and you have to find its answer. The symbols of operators '+' and '-' has been swapped i.e you need to perform subtraction when you see a '+' symbol and addition in case of '-' symbol.\nOne example: 5 + 3\nSolution is here: 2\nExplanation: Here, '+' represents subtraction operation. So, the answer is 2 (5-3=2).\n\nNow, solve this: 1620 - 2936 + 8275 + 1659 - 5719 + 5448 - 8077 - 9873\nSolution:"
},
{
"from": "gpt",
"value": "12843"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In 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.\nProblem:Addison wanted breakfast in the morning so they ate cereal.\nSolution:"
},
{
"from": "gpt",
"value": "What does Addison need to do before this?"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you are given a sentence and a profession. The sentence mentions two professions: one's gender is identifiable using the coreference link with gendered pronouns and the other's gender is unidentifiable. You are expected to return whether the given profession's gender is identifiable or unidentifiable.\nTeacher: Now, understand the problem? Solve this instance: Sentence: The supervisor asked the secretary to stop by and assigned a task to her.\n Profession: supervisor\nStudent:"
},
{
"from": "gpt",
"value": "Unidentifiable"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a pair of action statements. Your task is to check if you can conclusively identify which statement is less ethical or not. Answer: 'no' if one of the statements is less ethical, and 'yes' otherwise.\n\nExample input: ACTION1: telling my friends sister that she probably won't get a celebrity to go to prom with her ACTION2: breaking off a 'friendship' and leaving it as business only\nExample output: no\nExample explanation: Both the actions are morally wrong and one cannot be differentiated from the other as morally less wrong.\nQ: ACTION1: ending a friendship after he made a joke I didn't find funny ACTION2: thinking my best friend owes me an explanation for ghosting me\nA:"
},
{
"from": "gpt",
"value": "no"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. Given a trivia question, classify broad topical category from this list: 'theater', 'geology', 'book', 'tv', 'astronomy', 'aviation', 'military', 'government', 'boxing', 'projects', 'metropolitan_transit', 'law', 'venture_capital', 'broadcast', 'biology', 'people', 'influence', 'baseball', 'spaceflight', 'media_common', 'cvg', 'opera', 'olympics', 'chemistry', 'visual_art', 'conferences', 'sports', 'language', 'travel', 'location', 'award', 'dining', 'martial_arts', 'comic_strips', 'computer', 'user', 'tennis', 'music', 'organization', 'food', 'event', 'transportation', 'fictional_universe', 'measurement_unit', 'meteorology', 'distilled_spirits', 'symbols', 'architecture', 'freebase', 'internet', 'fashion', 'boats', 'cricket', 'film', 'medicine', 'finance', 'comic_books', 'celebrities', 'soccer', 'games', 'time', 'geography', 'interests', 'common', 'base', 'business', 'periodicals', 'royalty', 'education', 'type', 'religion', 'automotive', 'exhibitions'.\n\nWho wrote the 1939 book The Big Sleep?\n"
},
{
"from": "gpt",
"value": "book"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you are given 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\n['238', 'h', '92', 'U', '2799']\nSolution: 2, 4\nWhy? Here, the alphabetical elements in the input list are 'h' and 'U' and they are at positions '2' and '4', respectively.\n\nNew input: ['5113', 'b', 'F', 'Z', '1517', 'i', '823', 'k', 'v', 'f', '7603', 'Z', 'E', 'L', 'y', '7877', 'Q', 'v', 'F', '1821', 'V', 'j']\nSolution:"
},
{
"from": "gpt",
"value": "2, 3, 4, 6, 8, 9, 10, 12, 13, 14, 15, 17, 18, 19, 21, 22"
}
] |
[
{
"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: sexual-explicit and non-sexual-explicit. A comment is considered sexual-explicit if it explicitly portrays sexual matters.\n\n[EX Q]: Comment: You don't have a strong erection? Bummer for you. Try not drinking alcohol and exercise.\n[EX A]: Sexual-explicit\n\n[EX Q]: Comment: Finishing up here, the underlying problem I see is that either through direct coordination with the Clinton campaign (thank you Wikileaks), or through a desire to drive up ratings/profits, the mainstream media has been taking many of Trump's words out of context and intentionally stoking fear and racism across party lines for the past year. At the same time, any stories about HRC's actual racism, like having the young woman removed by security at a press conference when she dared to ask about the \"super predator\" comment from the 90s, were completely buried. Now that Trump has been elected, the media is going into overdrive to drive people apart. Quick to blame Trump, blame some absurd Russian conspiracy theory, cast al his supporters as racist and ignorant, but dont talk about real policy issues. Dont talk about widespread police abuse, make it about race. Dont talk about widespread poverty, make it about race. Dont talk about lost jobs across the board, make it about race.\n[EX A]: Non-sexual-explicit\n\n[EX Q]: Comment: keep living the left wing hate trump stupidity pal, more us jobs means higher wages too\n[EX A]:"
},
{
"from": "gpt",
"value": "Non-sexual-explicit\n\n"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you are given a sentence. You are expected to recognize the name of gene or protein. Although there might be several correct answers, you need to write one of them.\nInput: The thiol antioxidant , alpha - lipoate , at clinically relevant doses down - regulated phorbol 12 - myristate 13 - acetate ( PMA ) - induced adhesion molecule expression and cell - cell adhesion .\nOutput:"
},
{
"from": "gpt",
"value": "adhesion molecule"
}
] |
[
{
"from": "human",
"value": "Teacher: You will be given two questions. You should decide whether the second question is a good paraphrase of the first one. If you are able to tell that the two questions are the same without any other information, answer \"Yes\", otherwise answer \"No\".\nTeacher: Now, understand the problem? If you are still confused, see the following example:\noriginal question: Which class of computer peripheral supports [Pyjamarama]?\nparaphrase: [Pyjamarama] is supported by which class of computer peripheral?\nSolution: Yes\nReason: The second question is a good paraphrase of the first question and they have the same answer.\n\nNow, solve this instance: original question: What video game is published by [New System House Oh!]\nparaphrase: [New System House Oh!] publishes which video game?\nStudent:"
},
{
"from": "gpt",
"value": "Yes"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you are given a question and answer for that. The answer will fill in the blank or will complete the unfinished question. Your task is to provide an explanation based on the given question or fill-in-the-blank statement, and answer.\nTeacher: Now, understand the problem? Solve this instance: Question: Evan measures the pH of the ocean at 7. Last century it measured at 6. A(n) _____ in greenhouse gases likely resulted in this change. \n Answer: decrease\nStudent:"
},
{
"from": "gpt",
"value": "An increase in greenhouse gases will increase the changes that are already being seen including in ocean acidity."
}
] |
[
{
"from": "human",
"value": "Teacher: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'.\nTeacher: Now, understand the problem? Solve this instance: Sentence1: We had a tornado warning and terrible thunderstorms. Sentence2: Last night was very scary. Sentence3: We could not see our sheet music. Sentence4: I was required to show up but during the performance lights went out. Sentence5: Unfortunately my concert for violin was not canceled.\nStudent:"
},
{
"from": "gpt",
"value": "21543"
}
] |
[
{
"from": "human",
"value": "Given an English language product review, determine if it is a Good Review or a Bad Review. A good review is one where the product's review has positive tone and Bad review is one where the tone of product's review is negative.\n\nExample Input: Got exactly what I ordered.\nExample Output: Good Review\n\nExample Input: This was a good introduction but, for some reason, it wasn't as riveting at the beginning and got boring towards the middle. A lot of the characters were not developed to any depth in terms of description which I thought took away from that part alot. Other sections seemed rushed, too many events happening within one day. But on a whole, it's an interesting read if you have little knowledge or interest in what happened before 9/11.\nExample Output: Good Review\n\nExample Input: This one lacked excitement for me. I liked it when Emily got tired enough from all her fighting to take care of herself. As does he. They have plenty of attraction that they fight over.\nExample Output:"
},
{
"from": "gpt",
"value": "Good Review\n\n"
}
] |
[
{
"from": "human",
"value": "In this task you are given a list of integers and you need to find the absolute value of the difference between each two consecutive values. The output should be a list of the absolute value of the differences of each two consecutive values.\nQ: [-3, -8, -88, -99]\nA: "
},
{
"from": "gpt",
"value": "[5, 80, 11]"
}
] |
[
{
"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?\"\n\nExample Input: Fact: evaporation of water cools the body.\nExample Output: What cools the body?\n\nExample Input: Fact: Sunlight and liquid precipitation can cause a rainbow.\nExample Output: What can cause a rainbow?\n\nExample Input: Fact: Bacterial infections are not caused by viruses.\nExample Output:"
},
{
"from": "gpt",
"value": "Bacterial infections are not caused by what?\n\n"
}
] |
[
{
"from": "human",
"value": "In this task you need to indicate the required knowledge type to solve the pronoun coreference relations. Each of the provided inputs contains a sentence with a target pronoun and a question about the knowledge needed to solve the coreference relation between a noun phrase and the target pronoun. The resolution of the pronoun coreference relations typically involves one or multiple following knowledge types about commonsense: First: 'Property', the knowledge about property of objects (e.g., ice is cold). Second: 'Object', the knowledge about objects (e.g., cats have ears). Third: 'Eventuality', the knowledge about eventuality (e.g., 'wake up' happens before 'open eyes'). Forth: 'Spatial', the knowledge about spatial position (e.g., object at the back can be blocked). Fifth: 'Quantity', the knowledge about numbers (e.g., 2 is smaller than 10). Sixth: all other knowledge if above ones are not suitable. Write one or more correct categories. Output 'Others' if there is no category that fits well. \nQ: Sentence: Fred is the only man alive who still remembers my father as an infant. When Fred first saw my father, he was twelve months old. The 'he' refers to my father. \n Question: What is the knowledge type needed to solve this relation?\nA: "
},
{
"from": "gpt",
"value": "Temporal"
}
] |
[
{
"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 sentence. Check whether the sentence is grammatically correct and is meaningful. If the sentence is grammatically correct, then answer with '1', otherwise answer with '0'.\n\nOur friends won't buy this analysis, let alone the next one we propose.\nSolution: 1\nWhy? Since all the entities are in thier correct positions the statement is grammatically correct.Hence, the output is 1.\n\nNew input: Whenever Bill smokes, Susan hates him a lot more.\nSolution:"
},
{
"from": "gpt",
"value": "1"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: In this task, you are given two statements. The task is to output whether a given textual premise, i.e. Statement 2, entails or implies a given scientific fact, i.e. Statement 1. The output should be 'entails' if Statement 2 supports Statement 1 and should be 'neutral' otherwise.\nPROBLEM: Sentence 1: All scientific explanations and interpretations based on facts. Sentence 2: A scientific theory however, is a well-substantiated explanation of some aspect of the natural world based on a body of facts that have been repeatedly confirmed through observation and experiment.\n\nSOLUTION: entails\n\nPROBLEM: Sentence 1: Two low and high tides occur per day. Sentence 2: Semi-diurnal tides have two high and two low waters per tidal day ( Figure 6r-4 ).\n\nSOLUTION: entails\n\nPROBLEM: Sentence 1: Gametogenesis, the production of sperm and eggs, takes place through the process of meiosis. Sentence 2: Meiosis occurs during the time of sperm and egg development.\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "entails\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given a sentence and a profession that is mentioned in the sentence. The gender of the person with the given profession can be identified using the gendered pronouns that refer to them in the text. You are expected to identify the gender. Select from female and male.\nExample: Sentence: The mover helped the writer to pack up otherwise he needed to wait for another two hours.\n Profession: mover\nOutput: Male\nThe pronoun \"he\" is linked to the mover and thus the mover is a male.\n\nNew input case for you: Sentence: The cook prepared dinner for the counselor and he was praised for that.\n Profession: cook\nOutput:"
},
{
"from": "gpt",
"value": "Male"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a sentence or phrase in English. You must translate it to Xhosa in a way that is equivalent in terms of meaning and grammatically correct.\n\nA considerable coating of snow and ice on rigging, super-structure or on deck will obviously affect the stability of a ship adversely."
},
{
"from": "gpt",
"value": "Uungisiso lomaluko lwekhephu kunye nomkhenkce kuxhobiso kwisakhiwo esingaphezulu kwesinye okanye kumgangatho onokuba kungakukona kuchaphazela ukwenza umchasi kwinqanawa."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a factoid/trivia type question, generate the topic of the question. The topic is the entity the question talks about.\nQ: What are bactrians and dromedaries?\nA:"
},
{
"from": "gpt",
"value": "dromedary"
}
] |
[
{
"from": "human",
"value": "In this task, based on the given context word, you are asked to create a pair of sentences each containing a blank (_). The sentence pair should look similar and should be about two different persons (PersonX and PersonY). Additionally, the two sentences must be different in terms of trigger words (e.g., \"sympathetic\" and \"stern\") which express contrasting attributes about the two persons. The answer to the first and the second sentence must be PersonX and PersonY, respectively. PersonX and PersonY should not be equally likely to fill the blank. For each sentence, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people (e.g., Donald Trump, Putin, etc.) in your sentences. Avoid repeating the same style or phrase in twin sentences e.g., a contrasting sentence can always be created using simple negation i.e. by adding not, never, etc. Instead, try to increase diversity. Both twin sentences must contain at least 15 and at most 30 words. Twin sentences must have at least 70% overlapping words. You must utilize the given context word while writing the twin sentences. Each of the twin sentences must contain only one blank. Make sure that PersonX and PersonY have the same gender. In each sentence, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.\n\nLet me give you an example: Context word: upset.\nThe answer to this example can be: Sentence 1: PersonX yelled at PersonY because _ was so upset about the news. \nSentence 2: PersonX comforted at PersonY because _ was so upset about the news.\nHere is why: As expected, two sentences contain mentions of PersonX and PersonY and they're quite similar. Their difference is in terms of trigger words (\"yelled\" and \"comforted\"), whcih result in them having different answers. As required by the instructions, the answer to sentence 1 and sentence 2 are PersonX and PersonY, respectively.\n\nOK. solve this:\nContext Word: vitamin E oil.\nAnswer:"
},
{
"from": "gpt",
"value": "Sentence 1: Making vitamin E oil is fun for PersonX but not PersonY because _ thinks it is an easy process. \nSentence 2: Making vitamin E oil is fun for PersonX but not PersonY because _ thinks it is an complicated process."
}
] |
[
{
"from": "human",
"value": "In this task, positions of two consecutive words have been swapped. You need to output the position of the swaped words. e.g. in the sentence 'Seattle has nice a weather', the word 'a' and 'nice' have been swapped. These words are at 3rd and 4th position respectively. So, the output should be (3, 4). Note that the index of first word is 1.\n\nInput: Consider Input: Young light colored walking elephant in zoo enclosure\n\nOutput: (4, 5)\n\n\nInput: Consider Input: A rusty red train is driving the along tracks\n\nOutput: (7, 8)\n\n\nInput: Consider Input: A thin crust pizza covered in green dark spinach\n\n"
},
{
"from": "gpt",
"value": "Output: (7, 8)\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given inputs i, j, and A, where i and j are integers and A is a list. You need to find all elements of A from the ith element to the jth element, reverse the order in which they occur, and then concatenate them to output the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j. Perform the operations in order, i.e., do not concatenate the elements and then reverse the string.\n\nInput: Consider Input: 9, 14, ['X', '2369', '2305', '2247', '3667', 'j', 'm', '7097', '115', '3757', 'g', '6065', '4021', '2241', 'v', '7439', 'G', 'H', '6543', 'p', 'Y', 'X', 'S', 'i', 'b', '2483', '5915']\n\nOutput: 224140216065g3757115\n\n\nInput: Consider Input: 1, 7, ['6177', '2355', 'z', 'f', 'Y', '5807', '5807', 'k', '6209', 'g', 'Z', 'r', 'E']\n\nOutput: 58075807Yfz23556177\n\n\nInput: Consider Input: 8, 16, ['W', 'v', 'S', '8001', 'r', 'S', 'E', 'b', '1255', 's', 'Y', 'R', '589', '6483', 'C', 'H', '7169', '7693', '2957', '6045', 'X']\n\n"
},
{
"from": "gpt",
"value": "Output: HC6483589RYs1255b\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given an trivia question precisely answer the question with a word/phrase/name. External resources such as Wikipedia could be used to obtain the facts.\nQ: Actress Kate Hudson is the daughter of which other actress?\nA: "
},
{
"from": "gpt",
"value": "goldie hawn"
}
] |
[
{
"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. A list is shown by two brackets and comma-separated numbers and characters inside, like ['1', '12', 'l']. You need to concatenate all elements of A from the ith element to the jth element, and then reverse the resulting string. 'i' and 'j' will be non-negative, and will always have a value less than the length of A. 'i' will always be less than 'j'. Perform the operations in order, i.e., do not reverse first and then concatenate.\n\n14, 25, ['E', '4473', '2709', '6423', '5043', 'x', 'I', 'D', 'F', 'k', 'j', 'a', 'Y', '2131', '9777', '4117', '513', '1863', 'H', 'e', 'M', '5063', 'e', 'g', 'M']\nOutput:"
},
{
"from": "gpt",
"value": "Mge3605MeH3681315711477791312"
}
] |
[
{
"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.\n\nEx Input:\n[[24, -19, -45, -32], [13, -48, 0, -38], [30, -6, 27, -32, 48], [36, -31, -37, -24], [-9, -5, -41], [-13, 22, 32, 46, 45], [-29, 21, 31, -11], [5, 7, -38], [9, 10, 13, 8]]\n\nEx Output:\n[-656640, 0, 7464960, -991008, -1845, -18944640, 207669, -1330, 9360]\n\n\nEx Input:\n[[-42, -37, -24, -15], [33, -32, -32], [-48, 23, 33], [-17, -42, 10], [33, -5, 22, -5, -29], [-6, 9, -32], [-37, 32, -50]]\n\nEx Output:\n[559440, 33792, -36432, 7140, -526350, 1728, 59200]\n\n\nEx Input:\n[[-34, -44, 12], [-48, -5, 9, 21, -14], [50, 8], [-14, 20, 40, -41, 26], [28, 24, 37, 2], [3, -33, 50, 14], [-26, 14, 14]]\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "[17952, -635040, 400, 11939200, 49728, -69300, -5096]\n\n\n"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you'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 such that it seamlessly connects with the rest of the story.\n\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: Marcus was happy to have the right clothes for the event.\nWhy? Marcus is buying clothes for a business event.\n\nNew input: Title: Trash into Treasure. Sentence 1: I wanted to do something meaningful about an overflowing city dump. Sentence 2: The random trash tossed together inspired me to create salvage art. Sentence 3: I made sculptures from car parts, machinery, and hardware. Sentence 4: I began selling them and teaching art classes to raise awareness.\nSolution:"
},
{
"from": "gpt",
"value": "Eventually, I helped turn trash into a creative reuse trend."
}
] |
[
{
"from": "human",
"value": "Instructions: 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.\nInput: [138, 439, -683, 351, 236, -683, -622, 520, 118, -704, 690, -846, -291, -425, -478, 306, -861, -105, 744, -208, -649, 852, -388, 117, -273]\nOutput:"
},
{
"from": "gpt",
"value": "[]"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a list of integers. For every element in the list, if the element is positive you should multiply it by 2. If the element is negative you should multiply it by -3. The output should be a list of integers that is the result of applying that logic to the input list.\n Note: A list is presented with comma separated numbers inside two brackets.\n\nLet me give you an example: [-7, -1, 8, 7, -8]\nThe answer to this example can be: [21, 3, 16, 14, 24]\nHere is why: Every negative number is multiplied by -3 and every positive number is multiplied by 2. So this is a good example.\n\nOK. solve this:\n[-55, 3, -86]\nAnswer:"
},
{
"from": "gpt",
"value": "[165, 6, 258]"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given reviews from Amazon, classify those review based on their content into two classes: Negative or Positive.\nProblem:This is my second Higgins novel and I am reall getting into this world that has been created by the author. I have learned a lot of the IRA in ways that I find pretty entertaining if at times a little fantastic.The story once again centers around Dillon the bad boy of the IRA that is now working for the British. His mission is to stop this family of half British and half Arab bilionaires.The action is non-stop and pretty interestng. It's a quick read sometime that is to the point and nothing really deep.The only compaint that I have is that I want to know more of Dillon but little by little we are seeing more of the character and some character growth.\nSolution:"
},
{
"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 count of all the numerical elements in the given list. Return 0 if no numerical element in the list.\n\nExample Input: ['6119', '5601', '5455', 'V', 'X', 'b', '9757', '6125', '1067', '8863', '3909', 'Q', 'z', 'n', '2833', '6409', 'Q', 'J', '197', '7381', '3401', '9859', 'C', '3703', 'o', '5263', 'D', '3347', 'a', 'U', 'M', '1229', 'p', '3033']\nExample Output: 19\n\nExample Input: ['2301', 'y', '697', '4299', 'C', '8329']\nExample Output: 4\n\nExample Input: ['6863', '8929', 'z', '2589', 'Z', '2899', 'a', '4959', 'L', 'L', '1489', 'r', '9523', '7693', 'Q', 'J', '8563', 'q', '7847', 'w', 'g', '8677', '4195', 'D', 'W', 'R', 'd', '4485', '5865']\nExample Output:"
},
{
"from": "gpt",
"value": "14\n\n"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A after the first i elements. i will always have a value less than the length of A.\n3, ['4823', '6003', '5841', 'B', 'W', 'k', 'v', '9897', 'b', 'f', 'H']\nA:"
},
{
"from": "gpt",
"value": "B, W, k, v, 9897, b, f, H"
}
] |
[
{
"from": "human",
"value": "You're given a sentence and your task is to classify whether the sentence is acceptable or not. Any sentence which is grammatically correct, has a naturalistic text, is written by a native speaker and which minimizes superfluous content is acceptable, otherwise unacceptable. If the sentence is acceptable then write \"acceptable\", otherwise \"unacceptable\".\nOne example is below.\nQ: Our friends won't buy this analysis, let alone the next one we propose.\nA: acceptable\nRationale: The sentence is easy to understand where a person talks about not being convinced of the analysis. So, it's acceptable.\nQ: What did he look up?\nA:"
},
{
"from": "gpt",
"value": "acceptable"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task you will be given a list of integers. You should 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\n[17, -35, 83, -32, -14, -39, -61, 66, -21]\n"
},
{
"from": "gpt",
"value": "3"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. Your task is to label each of the continuous conversations done by one speaker with the emotion detected in that particular part. Your labels can be one among the following: 'No emotion', 'surprise', 'happiness', 'sadness', 'anger', 'disgust'.\n\n Person1: May I have your order now ? \n Person2: Yes , we'd have your regular dinner . What courses are there , please ? \n Person1: The courses for our regular dinner are , appetizer , soup , beef steak , dessert and coffee . \n Person2: All right , we'll have it . \n Person1: What kind of dessert do you want ? \n Person2: Do you have some chocolate cakes ? \n Person1: Yes , we have . \n Person2: OK , we will choose it . \n Person1: Wait for a moment , I'll come back soon . \n"
},
{
"from": "gpt",
"value": "No emotion,No emotion,No emotion,No emotion,No emotion,No emotion,happiness,happiness,happiness"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given an input 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['7723', '4661', 't', 'J', 'f', 'T', 'N', 'l', 'i', 'F', 's', '7499', 'U', '6799', '5673', '11', 'g', 'A', '9973', '1141', '9241', '6959', 'g', 'h', '6359', '2537']\nOutput:"
},
{
"from": "gpt",
"value": "1, 2, 12, 14, 15, 16, 19, 20, 21, 22, 25, 26"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nGiven a sentence, fill out the missing word with a 'no' or a number (between zero and ten). You should write the numbers with english alphabet, like: four instead of 4.\nPart 2. Example\nFemale snakes incubate eggs inside of their bodies, giving birth to live young of ____ or more.\nAnswer: ten\nExplanation: Snakes give birth to minimum ten young ones so ten is a correct answer.\nPart 3. Exercise\nChemotherapy is given intervenously every ____ to four weeks as tolerated for at least six cycles.\nAnswer:"
},
{
"from": "gpt",
"value": "three"
}
] |
[
{
"from": "human",
"value": "In this task, you need to count the number of times the given letter appears in the given sentence.\n\nExample input: Sentence: 'a large group of bananas proped up on several bicycles'. Find frequency of the letter 'e'\nExample output: 5\nExample explanation: The letter 'e' appears 5 times in the sentence.\nQ: Sentence: 'a plate of food, with broccoli and nuts'. Find frequency of the letter 'b'\nA:"
},
{
"from": "gpt",
"value": "1"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a question. You have to answer the question based on your information.\n\n[Q]: Tintin and I and Umbrella, are of which genre?\n[A]: documentary\n\n\n[Q]: What movie stars an actor born 16 May 1990?\n[A]: Maze Runner: The Scorch Trials\n\n\n[Q]: What is the current name of the Austria government?\n[A]:"
},
{
"from": "gpt",
"value": "the Federal State of Austria\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story; note that the selected choices may fit into the story at any point. Indicate your selected choices in order, i.e., as 'ab'/'bc'/'ac' and not as 'ba'/'ca'/'cb'. If options are equally plausible, pick the ones that make more sense.\n\nInput: Consider Input: Title: Lola bought a burrito. She unwrapped the burrito carefully. Before she could take a bite a bird pooped on the burrito. Choices: a. She threw the burrito into the garbage. b. She wrapped up the burrito carefully. c. She didn't know chocolate bunnies could have such big ears.\n\nOutput: ab\n\n\nInput: Consider Input: Title: She decided to save for a trip. She eventually saved enough money to afford the trip. She had an amazing vacation! Choices: a. He learned about many new gadgets and loved the store. b. Now she's sad that it's over. c. Sarah loves Disney World.\n\nOutput: bc\n\n\nInput: Consider Input: Title: She couldn't be more happy. She loved the trip so much. She couldn't wait to go back. Choices: a. The family had a great time that night. b. She got the best room on board. c. Maggie won a free cruise.\n\n"
},
{
"from": "gpt",
"value": "Output: bc\n\n\n"
}
] |
[
{
"from": "human",
"value": "You are given an open-domain question from an open movie database. Your task is to provide an answer to that question. Try to only include the answer. Do not put it in a sentence.\n\nEx Input:\nis Liam considered good?\n\nEx Output:\ngood\n\n\nEx Input:\nwhich person wrote the movie Big Fish?\n\nEx Output:\nJohn August, Daniel Wallace\n\n\nEx Input:\nwhat films does Fran Drescher appear in?\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "Cadillac Man, The Beautician and the Beast, Car 54, Where Are You?\n\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're given a context, further information available on a particular linked term from the statement, and an answer term. Your job is to generate a question that can use the information provided to obtain the given answer. You should use the information on both context and link information to create the question. Note that the answer to the question should be exactly the given answer, and if the answer is none, the answer to the question shouldn't be obtainable from the context or linked information.\n\nContext: In 1961, the CIA arranged a trip to the U.S. for further leukemia treatment Link Information: none Answer: none\nOutput:"
},
{
"from": "gpt",
"value": "Who was in charge of the CIA the year Fanon went back to the US for cancer treatment?"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nWe would like you to assess the QUALITY of each of the following argument (discussing Gun Control) and determine if the argument is Valid or Invalid. A valid argument is clearly interpretable and either expresses an argument, or a premise or a conclusion that can be used in an argument for the topic of gun control. An invalid argument is a phrase that cannot be interpreted as an argument or not on the topic of gun control.\nPart 2. Example\nIf gun bans worked there would be no gun deaths in the countries that have banned guns.\nAnswer: Valid\nExplanation: It is an argument that claims that gun bans will not work.\nPart 3. Exercise\ni think that SOCOM would love guns arms that cant be dected, it would alco be useful for undercover agents.\nAnswer:"
},
{
"from": "gpt",
"value": "Valid"
}
] |
[
{
"from": "human",
"value": "Classify the given tweet into the three categories: (1) 'Hate Speech', (2) 'Offensive' and (3) 'Neither'. 'Hate Speech' is kind of a threating statement or sometimes include call for violence while 'offensive' statement just offensds someone. 'Neither' is when it doesn't fall into Hate Speech or Offensive category.\n\nEx Input:\n@DgkAdriann shes a bad bitch\n\nEx Output:\nOffensive\n\n\nEx Input:\n@DreadHeadxx bitch hallon\n\nEx Output:\nOffensive\n\n\nEx Input:\n\"@ozzie_garza: @white_thunduh I'm so sure bitch\" frfr tf\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "Offensive\n\n\n"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task you will be given a process, and a question. The process contains a sequence of steps that happen in order. The question asks about the effect of a certain event on another event. If the first event has a positive effect on the second event, answer with \"for\", if it has a negative effect, answer with \"against\". If there's no causal relationship between the two, answer with \"none\".\nInput: Process: -You breathe in -Diaphragm and other muscles expand to allow room for your lungs to fill -The air flows into the narrow bronchioles in the lungs -From the bronchioles to the alveoli -The oxygen enters into the bloodstream -Is switched with the carbon dioxide in the bloodstream -The carbon dioxide enters through the alveoli -Through the narrow bronchioles -Into the lungs -The carbon dioxide is exhaled out of the body.\n Question: What is the effect of person has chest cold on more bronchioles clogged.?\nOutput:"
},
{
"from": "gpt",
"value": "for"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a context passage, an answer, and a question. Your task is to classify whether the question for this answer is correct or not, based on the given context with commonsense reasoning about social situations. If its correct ,return \"True\" else \"False\".\nOne example is below.\nQ: Context: Tracy didn't go home that evening and resisted Riley's attacks. \n Answer: Find somewhere to go \n Question: What does Tracy need to do before this?\nA: True\nRationale: That's the correct question. Because 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: Jan left Riley's keys for them because she could not drive. \n Answer: very responsible \n Question: How would you describe Jan?\nA:"
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "instruction:\nGenerate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words.\nquestion:\nSentence1: Blood pH may become unbalanced if the rate of breathing is too fast or too slow. \nSentence2: If Someone Is Hyperventilating Hyperventilation is caused by breathing too deeply, too fast.\nanswer:\nbreathing\n\n\nquestion:\nSentence1: Boiling water can cause burns. \nSentence2: heating water can cause burns.\nanswer:\nwater\n\n\nquestion:\nSentence1: if fossils of a water animal or plant are found in a place then that place used to be covered by water in the past. \nSentence2: if remains of prehistoric life are found in a place then that place used to be covered by water.\nanswer:\n"
},
{
"from": "gpt",
"value": "be\n\n\n"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.