Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "from": "human", "value": "You are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to find the correct answer (and return the string of the correct option, not option1/2) for the given question from the given options and based on the given passage. Answer of the question can be found directly from the passage.\n\nLet me give you an example: Passage: Omelettes make a great breakfast , and I enjoy making them because they are very easy to cook . First , I get the eggs out and begin cracking them on the side of the bowl and dumping them into the bowl . I normally use two eggs whites and one whole egg to cut the calories . I add some salt and pepper to the mix for flavor . I pour the mixture into the hot frying pan . I make sure that I add some vegetable oil to the pan before I add the eggs though because I do n't want them to stick . As this occurs , I add some cheese or vegetable to the center of the egg mixture . Really , almost any type of cheese or vegetable makes a good omelette . I then flip one side of the omelette over on to itself to seal in the contents in the middle . It is then ready to serve ! Question: How many times is the omelette flipped? Option1: three times Option2: once\nThe answer to this example can be: once\nHere is why: As mentioned in the passage that I then flip one side of the omelette; it is clear that omelette is flipped one time only.\n\nOK. solve this:\nPassage: Today I went to a football match with my friend Alex. Alex and I met at his house and drove together from there . We paid $ 5 each for our tickets at the gate , and stopped to buy popcorn before making our way to our seats . We sat in the seventh row , close to the field . The players ran out onto the field and we cheered loudly for our team . The ball started with the opposing team but our star player kicked it away and made a goal . We stood up and cheered . The teams were well paired and many goals were blocked by the keepers for each team . We hardly stayed in our seats . In the end our team one and we were very happy . Question: What was the outcome of the match? Option1: The narrator's preferred team won Option2: the other team won\nAnswer:" }, { "from": "gpt", "value": "The narrator's preferred team won" } ]
[ { "from": "human", "value": "In this task, you are given a sentence with a missing word that can be an object, a person, and/or an action. Fill in the blank with a plausible word. Although each sentence has many correct answers, you only have to write one answer.\nQ: PersonX maintains the patient 's ___\nA: " }, { "from": "gpt", "value": "bathroom" } ]
[ { "from": "human", "value": "The provided file includes inquiries about restaurants, and we ask you to translate those to the Italian language. Please bear in mind the following guidlines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are NOT looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks SHOULD NOT be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 SHOULD NOT be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for special placeholders. Please do the same in your translations.\nOne example is below.\nQ: are there any \" italian \" restaurants nearby with 6 star reviews ?\nA: ci sono ristoranti \" italian \" nelle vicinanze con valutazioni di 6 stelle?\nRationale: The translation correctly preserves \" italian \" entity and is accurate\nQ: look up a \" mexican \" restaurant for me .\nA:" }, { "from": "gpt", "value": "cerca un ristorante \" mexican \" per me." } ]
[ { "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.\n\nEx Input:\n6570 + 2902 + 9219 - 6971 + 6886 + 765\n\nEx Output:\n-6231\n\n\nEx Input:\n4264 - 4438 + 3871 + 7585 - 540 - 3455 - 6016\n\nEx Output:\n7257\n\n\nEx Input:\n9301 + 1619 - 7459 + 5871 + 2497 + 4093 + 7957 - 1085 - 6698\n\nEx Output:\n" }, { "from": "gpt", "value": "2506\n\n\n" } ]
[ { "from": "human", "value": "Given a set of four words, generate the category that the words belong to. Words are separated by commas. The possible categories are social gathering, accomodation, physical property, measurement unit, corporate, nutritional value, boats, police punishment, location (proximity), card games, outdoor sport activity, military rank, baby animals, weather, consumer product, animals, boxing terminology, food, chocolate food, bird, type of sandwich, date status, body part, ocean, employment activity, moral characteristic, elements, poker, computers, construction, guitar part, shady activities, physical activity, kitchenware, temperature, type of rigidity, emotional status, season, mode of transportation, window material, activity, emotional display, geographical property, fried food, store status, widespread, aesthetic characteristic, alcoholic drinks, secretary duty, direction, personal characteristic, and animal.\n\nderrick, sandpiper, goose, crane\nbird\n\nthing, content, substance, books\nconsumer product\n\negret, flamingo, crane, swift\n" }, { "from": "gpt", "value": "bird\n\n" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you will be presented with a question, and you have to write the part-of-speech tag for each word in the question. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb\nExample: Who were the builders of the mosque in Herat with fire temples ?\nOutput: WP VBD DT NNS IN DT NN IN NNP IN NN NNS .\nThis is a good example. All of the POS tags are correct.\n\nNew input case for you: How many sound stages make up the venue located in the sixth-largest metropolitan area in the Southern US ?\nOutput:" }, { "from": "gpt", "value": "WRB JJ JJ NNS VBP RP DT NN VBN IN DT JJ JJ NN IN DT NNP NNP ." } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven a sentence in English language, translate the sentence to Somali language keeping the meaning of the original sentence intact\n\nEnglish sentence: Physical and Sports Activities department (DAPS)\nOutput:" }, { "from": "gpt", "value": "waaxda Jirka iyo Sports Hawlaha (DAPS)" } ]
[ { "from": "human", "value": "Detailed Instructions: \"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). Given a prompt and two responses, identify which response is the type of \"yes, and\". Indicate your answer by 'Response 1' if the first response is correct, otherwise 'Response 2'. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange.\nQ: Prompt: You have to have some green chilies before you leave Santa Fe. \n Response 1: So what, you're going to put the lids back on the tubs? \n Response 2: Those sound spicy. Are they spicy? I have a sensitive stomach.\nA:" }, { "from": "gpt", "value": "Response 2" } ]
[ { "from": "human", "value": "Instructions: 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.\nInput: ['a', 'I', 'J', 'Z', 'P', '5821', '7435', '299', '1715', 'M', 'O', 'z', 'n', 'f', '9437', '3073', 'D', 'C', 'n', '5231', 'h', '535', '8035', 'M', 'i', 'I', 'z', 'w', '2643', '7083', '8471', '2135', '655', '1935', 'i', '5439', '7991']\nOutput:" }, { "from": "gpt", "value": "17" } ]
[ { "from": "human", "value": "Instructions: In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to determine which two sentences need to be swapped sentences in order to make a story that makes complete sense and is befittingly titled. Indicate your answer using the numbers of the two sentences in order, such as '34' or '25'. The first digit refers to the sentence which should come first in the story.\nInput: Title: A Wedding. Sentence 1: Josh wanted to get married in his boyhood church. Sentence 2: He loved seeing his old pastor and his old church friends. Sentence 3: On the day of the wedding he had a great time. Sentence 4: He convinced his fiance to go ahead with the plans. Sentence 5: Josh had the wedding of his dreams.\nOutput:" }, { "from": "gpt", "value": "42" } ]
[ { "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.\nQ: 4685 - 3751 - 5266 + 2023 - 1398 + 9926 - 5442 + 9160 - 6231\nA: " }, { "from": "gpt", "value": "5664" } ]
[ { "from": "human", "value": "In this task you will be given a question and a passage. You need to determine if the answer to the question is contained in the passage. If the answer can be found in the passage you should output 'True'. If the answer cannot be found in the passage you should output 'False'.\n\nInput: Consider Input: Passage: ''Tropical' refers to the geographical origin of these systems, which form almost exclusively over tropical seas. 'Cyclone' refers to their winds moving in a circle, whirling round their central clear eye, with their winds blowing counterclockwise in the Northern Hemisphere and blowing clockwise in the Southern Hemisphere. The opposite direction of circulation is due to the Coriolis effect. Tropical cyclones typically form over large bodies of relatively warm water. They derive their energy through the evaporation of water from the ocean surface, which ultimately recondenses into clouds and rain when moist air rises and cools to saturation. This energy source differs from that of mid-latitude cyclonic storms, such as nor'easters and European windstorms, which are fueled primarily by horizontal temperature contrasts. Tropical cyclones are typically between 100 and 2,000 km (62 and 1,243 mi) in diameter.'. Question: 'why does tropical cyclone originated over the seas'.\n\nOutput: True\n\n\nInput: Consider Input: Passage: 'Worldwide, tropical cyclone activity peaks in late summer, when the difference between temperatures aloft and sea surface temperatures is the greatest. However, each particular basin has its own seasonal patterns. On a worldwide scale, May is the least active month, while September is the most active. In the Northern Atlantic Ocean, a distinct hurricane season occurs from June 1 to November 30, sharply peaking from late August through September; the season's climatological peak of activity occurs around September 10 each season. This is the norm, but in 1938, the Atlantic hurricane season started as early as January 3.'. Question: 'hurricane season peaks in the atlantic in september because'.\n\nOutput: True\n\n\nInput: Consider Input: Passage: 'A black panther is the melanistic color variant of any big cat species. Black panthers in Asia and Africa are leopards (Panthera pardus), and those in the Americas are black jaguars (Panthera onca).'. Question: 'why is facilitated diffusion not a form of active transport'.\n\n" }, { "from": "gpt", "value": "Output: False\n\n\n" } ]
[ { "from": "human", "value": "In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to classify the command into one of these seven categories: (1) majority, (2) unique, (3) superlative, (4) count, (5) comparative, (6) aggregation, and (7) ordinal. \n Here are the defications of each category: \n 1. majority: Describing the majority values (most or all) over one column, with the scope of all table rows or a subset of rows \n 2. unique: Describing one unique row, regarding one column, with the scope of all table rows or a subset of rows \n 3. Superlative: Describing the maximum or minimum value in a column, with the scope of all table rows or a subset of rows \n 4. Ordinal: Describing the n-th maximum or minimum value in a column, with the scope of all table rows or a subset of rows \n 5. Comparative: Comparing two rows in the table, regarding their values in one column \n 6. Count: counting some rows in the table based on the values in one column, with the scope of all table rows or a subset of rows \n 7. Aggregation: Describing the sum or average value over a column, with the scope of all table rows or a subset of rows. \n Here are the definitions of logical operators for understanding of command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\nLet me give you an example: round_eq { sum { all_rows ; casinos } ; 217 }\nThe answer to this example can be: aggregation\nHere is why: In this example sum returns the sum of the values in all of the casinos rows. Hence, aggregation is right category.\n\nOK. solve this:\neq { hop { nth_argmax { all_rows ; semifinalists ; 3 } ; country } ; sweden }\nAnswer:" }, { "from": "gpt", "value": "ordinal" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you're given context and an answer. Your task is to generate the question for this answer based on the given context with commonsense reasoning about social situations..\nExample: Context: Tracy didn't go home that evening and resisted Riley's attacks. \n Answer: Find somewhere to go\nOutput: What does Tracy need to do before this?\nTracy 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?\n\nNew input case for you: Context: jesse thanked the university for a grant and others were angry that they didn't get a grant. \n Answer: be jealous\nOutput:" }, { "from": "gpt", "value": "What will happen to Others?" } ]
[ { "from": "human", "value": "Generate an appropriate single-sentence summary for the given text such that it includes the main topic of the text.\nQ: By Barbara Plett UsherBBC News What's changed under Trump? The threat perception: The Americans believe that Pyongyang already has the technology to fire nuclear warheads at Japan and South Korea. And they calculate that it will likely be able to hit the United States within a few years. So North Korea is now seen as a threat to US national security, not only a menace to regional allies. Hence the sense of urgency and resolve. The rhetoric: Military options have always \"been on the table\", sometimes more actively than others. But rarely if ever has a US administration been as blunt or outspoken about it. That is largely a factor of President Trump's style but it's also due to growing concern about the imminence of the threat. The military posturing: Spring is usually a tense time in the Korean Peninsula, because North Korea celebrates a number of patriotic anniversaries that can serve as launch pads for weapons tests, and the US conducts military exercises with Seoul. But this year the Trump administration added to the firepower on display, including a submarine equipped with guided missiles, and an aircraft carrier group. The confusion over the deployment of the latter, however, may have detracted somewhat from its deterrent effect. North Korea: Pyongyang has long held that it needs nuclear weapons to guarantee its security, and has been ready to face down international censure and punishment. But Kim Jong Un has shown particular determination and, unlike his father and grandfather, a disregard for the views of his only major ally, China. \"Kim Jong Il for all of his sins at least cared what other people thought and particularly cared what the Chinese thought,\" the former US negotiator Chris Hill told the BBC. \"His son Kim Jung Un doesn't seem to care what anyone thinks.\" China: China is exasperated by its recalcitrant ally and worried about the growing sophistication of its weapons. It had already begun tightening its implementation of sanctions by following through with the UN's recent ban on coal imports. But it's probably even more worried that Trump's military posturing will escalate tensions, and uneasy about his insistence that Beijing is uniquely positioned to squeeze Pyongyang. In an apparent response to US pressure, Chinese newspapers have published tougher statements about North Korea. There's also been closer coordination between Beijing and Washington. The Secretary of State Rex Tillerson says Beijing has threatened Pyongyang with unilateral sanctions if it carries out a sixth nuclear test. What hasn't changed The options: There are still no good ones. Tillerson says denuclearisation would still be the goal, but he has not been precise about conditions for starting talks. The strategy: Actually, it has sort of changed and sort of hasn't. The administration says it has. But the components - pressing for tighter economic sanctions, urging China to lean on its neighbour, and waiting for North Korea to buckle - look a lot like Barack Obama's \"strategic patience\". The difference seems to be less patience, a more credible threat of military force, and more coercive diplomacy. Tillerson says the knob on the pressure campaign is at \"five or six\" right now, with the US \"testing\" Beijing's ability to influence North Korea, and threatening to sanction parties that violate the UN embargo. Alongside China, the Trump administration is also trying to convince South East Asian nations to isolate North Korea. China: China may be more willing to turn the screws on Pyongyang, but only so far. There is no sign that it has changed its calculation of North Korea as a buffer state. Beijing fears that if the regime collapses the American security umbrella will be extended across the peninsula right to its borders. And while North Korea is a dangerous headache, America is its biggest strategic rival. Tillerson's recent assurance that the US is not seeking regime change was aimed as much at Beijing as it was at Pyongyang. The wild card: Even with a nuclear rogue state, President Trump likes to be unpredictable. And his tactics are those of a deal maker. Nevertheless observers are struggling to interpret the contrast between his hardline rhetoric and his recent suggestion of a meeting with Kim Jong Un - under the \"right circumstances\" . Barack Obama also said during the 2008 election campaign he'd be willing to meet the North Korean leader. But he did not go on to praise his adversary as did Trump, calling him a \"smart cookie\" for holding onto power by wiping out his rivals. It's not clear if the president was deliberately dangling a carrot, making another overture among several to a strongman, or simply throwing an offhand comment into the mix.\nA: " }, { "from": "gpt", "value": "After weeks of tough talk and escalating tensions between the US and North Korea, President Donald Trump has referred to the possibility of meeting his opposite number, Kim Jong Un. Let's take a step back and look at how we got here." } ]
[ { "from": "human", "value": "Part 1. Definition\nGiven a sentence, generate a new sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\nPart 2. Example\nStimulating the mind helps the brain to grow essential neural cells .\nAnswer: Stimulating the learning helps the brain to grow new neural cells .\nExplanation: This is a good example of a change in the input. The created sentence is semantically similar to the input as both are talking about growing essential neural cells and the changes in the sentence follows the commonsense knowledge.\nPart 3. Exercise\nTelling a story requires validation .\nAnswer:" }, { "from": "gpt", "value": "Telling a story requires language." } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're given a review from Amazon. Your task is to generate a rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral, 4: good, 5: extremely good.\n\nOnly marking this down because I ordered 2 of the 3 packs and one of the packs was completely damaged. Emailed the company and never got a response or refund.\nOutput:" }, { "from": "gpt", "value": "1" } ]
[ { "from": "human", "value": "In this task, you're given a context, a question, and three options. Your task is to find the correct answer to the question using the given context and options. Also, you may need to use commonsense reasoning about social situations to answer the questions. Classify your answers into 'A', 'B', and 'C'.\nQ: Context: Kendall wanted to help Casey get hired for her new job. \n Question: Why did Kendall do this? \n Options: (A) make Casey get hired (B) hurt Casey's prospects (C) stop Casey from getting hired\nA: " }, { "from": "gpt", "value": "A" } ]
[ { "from": "human", "value": "instruction:\nIn this task, you need to provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are fine 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 : '$': Dollar Sign, \"''\": Single Quotes, ',': Comma Symbol, '-LRB-': Left Parantheses, '-RRB-': Right Parantheses, '.': Period, ':': Colon, 'ADD': Email Address, 'AFX': Affix, 'CC': Coordinating conjunction, 'CD': Cardinal Number, 'DT': Determiner, 'EX': Existential there, 'FW': Foreign Word, 'GW': Go with, 'HYPH': Hyphen symbol, 'IN': Preposition or a subordinating conjunction, 'JJ': Adjective, 'JJR': A comparative Adjective, 'JJS': A Superlative Adjective, 'LS': List item Marker, 'MD': Modal, 'NFP': Superfluous punctuation, 'NN': Singular Noun, 'NNP': Singular Proper Noun, 'NNPS': Prural Proper Noun, 'NNS': Prural Noun, 'PDT': Pre-determiner, 'POS': Possessive Ending, 'PRP': Personal pronoun, 'PRP$': Possessive Pronoun, 'RB': Adverb, 'RBR': Comparative Adverb, 'RBS': Superlative Adverb, 'RP': Particle, 'SYM': Symbol, 'TO': To , 'UH': Interjection, 'VB': Base form Verb, 'VBD': Verb in Past tense, 'VBG': Verb in present participle, 'VBN': Verb in past participle, 'VBP': Verb in non-3rd person singular present, 'VBZ': Verb in 3rd person singular present, 'WDT': Wh-determiner, 'WP': Wh-pronoun, 'WP$' Possessive Wh-pronoun, 'WRB': Wh-adverb, 'XX': Unknown, '``': Double backticks.\nquestion:\nSentence: Laser grips are the {{ most }} common for wangs . \nWord: most\nanswer:\nRBS\n\n\nquestion:\nSentence: Mosques are calling for {{ donating }} blood , food , and medicine for Fallujah , and several convoys have already headed out for Fallujah , most of them returned later though . \nWord: donating\nanswer:\nVBG\n\n\nquestion:\nSentence: I know that if my garage door needs to be repaired , I will be calling A CLASS Garage {{ Doors }} \nWord: Doors\nanswer:\n" }, { "from": "gpt", "value": "NNPS\n\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you are given a sentence from the research paper and the category to which it belongs. Your task is to classify whether the given category is correct or not by providing \"True\" and \"False\", respectively. Here are the definitions for the categories: Background (Why is this problem important? What relevant works have been created before? What is still missing in the previous works? What are the high-level research questions? How might this help other research or researchers?), Purpose (What specific things do the researchers want to do? What specific knowledge do the researchers want to gain? What specific hypothesis do the researchers want to test?), Method (How did the researchers do the work or find what they sought? What are the procedures and steps of the research?), or Finding (What did the researchers find out? Did the proposed methods work? Did the thing behave as the researchers expected?). \",\n\nSentence: Efforts to control future SARS outbreaks depend on the accurate and early identification of SARS-CoV infected patients. \n Section: background\nSolution: True\nWhy? The section is correct because it provides the background information regarding how they could control future SARS outbreaks depending on the accuracy of identification of some infected patients having SARS-CoV.\n\nNew input: Sentence: outbreaks in schools and in general populations. \n Section: finding\nSolution:" }, { "from": "gpt", "value": "True" } ]
[ { "from": "human", "value": "Q: In this task, you're given statements in native Kannada language. The statement can be written with the Kannada alphabet or the English alphabet. Your job is to evaluate if the statement is offensive or not. Label the post as \"Not offensive\" if the post does not contain offense or insult. Non-offensive posts do not include any form of offense or insult. Label the post as \"Offensive\" if the post contains offensive language. \nLoo Nim Makha muccha e Video gu Dislike yenro nim Hendti Munde Haga avr character Nodi kaliro life Andre yenu antha thu nanmakla\nA:" }, { "from": "gpt", "value": "Offensive" } ]
[ { "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.\nQ: 13, ['1263', '3557', 'R', '3759', '5695', 'x', '7789', '6795', 'K', 'g', '5909', 'C', '59', '1845', 'v', '8867', 'X', '3773', 'x', '1005', '4853', 'w', '7205', 'D', 'N', 'Z', 'I', '8469', '6833', '2587', 'N', 'X', '9261', 'q', '903', '5887', '3755', 'O', 't', 'H', 'W', '9771', 'R', '6631', 'y', 'o']\nA: " }, { "from": "gpt", "value": "1263, 1845, I, H" } ]
[ { "from": "human", "value": "Given a sentence, generate what should be the most likely next statement. The next statement should be reasonable and logically correct.\n\nEx Input:\nThe man screws a nozzle onto a propane tank and fuels the fire with it. The fire\n\nEx Output:\nis put out with a bucket of water and covered in earth.\n\n\nEx Input:\nThe first carpenter sprays paint all over the ceiling. A couple of carpenters\n\nEx Output:\nsmooth out the paint on the ceiling.\n\n\nEx Input:\nA group of girls are on a field in front of spectators. They\n\nEx Output:\n" }, { "from": "gpt", "value": "are chasing a ball during a game of field hockey.\n\n\n" } ]
[ { "from": "human", "value": "\"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). Given a prompt and two responses, identify which response is the type of \"yes, and\". Indicate your answer by 'Response 1' if the first response is correct, otherwise 'Response 2'. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange.\nOne example is below.\nQ: Prompt: See, Arlene? That's why I don't talk to you like that because I'm afraid I'll scare our son. \n Response 1: I have 12. Wait, is the key to a success story getting the number to go down? \n Response 2: Oh, Dad. Even that wasn't great.\nA: Response 2\nRationale: Response 2 is correct answer because it agrees with the prompt and continues the conversation in the same context.\nQ: Prompt: I'm worried. I have a family and you've had me hold these knives all day. If I slip, this knife is going to go straight into my throat. \n Response 1: Or, it could go straight into his throat. \n Response 2: Maybe not, but I feel like I've got some good questions about life and stuff.\nA:" }, { "from": "gpt", "value": "Response 1" } ]
[ { "from": "human", "value": "Given an entity as input, output another entity which is part of the input entity. These are entities of meronym. In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., output entity) is in a part-of relationship with its holonym (i.e., input entity).\n\n[Q]: drosophila specie\n[A]: eye\n\n\n[Q]: ballast water\n[A]: pathogen\n\n\n[Q]: cavity\n[A]:" }, { "from": "gpt", "value": "muscle wall\n\n\n" } ]
[ { "from": "human", "value": "Teacher:In this task you're given a question and you have to paraphrase the question to create the output question while retaining the meaning of the original question.\nTeacher: Now, understand the problem? Solve this instance: What is the male equivalent of \"maiden name?\"\nStudent:" }, { "from": "gpt", "value": "My daughter wants to use my maiden name at new school. Can she without legally changing it, which she may do when she turns 18 (10/2016)?" } ]
[ { "from": "human", "value": "Detailed Instructions: This task is about writing a correct answer for the reading comprehension task. Based on the information provided in a given passage, you should identify the shortest continuous text span from the passage that serves as an answer to the given question. Avoid answers that are incorrect or provides incomplete justification for the question.\nProblem:Passage: In July 2013, three former supporters of Mayor Bob Filner asked him to resign because of allegations of repeated sexual harassment. Over the ensuing six weeks, 18 women came forward to publicly claim that Filner had sexually harassed them, and multiple individuals and groups called for him to resign. On August 19 Filner and city representatives entered a mediation process, as a result of which Filner agreed to resign, effective August 30, 2013, while the city agreed to limit his legal and financial exposure. Filner subsequently pleaded guilty to one felony count of false imprisonment and two misdemeanor battery charges, and was sentenced to house arrest and probation. Question: How long did Filner's trial last?\nSolution:" }, { "from": "gpt", "value": "six weeks" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task you are expected to write an SQL query that will return the data asked for in the question. An SQL query works by selecting data from a table where certain conditions apply. A table contains columns where every row in that table must have a value for each column. Every table has a primary key that uniquely identifies each row, usually an id. To choose which columns are returned you specify that after the \"SELECT\" statement. Next, you use a \"FROM\" statement to specify what tables you want to select the data from. When you specify a table you can rename it with the \"AS\" statement. You can reference that table by whatever name follows the \"AS\" statement. If you want to select data from multiple tables you need to use the \"JOIN\" statement. This will join the tables together by pairing a row in one table with every row in the other table (Cartesian Product). To limit the number of rows returned you should use the \"ON\" statement. This will only return rows where the condition specified after the statement is true, this is usually an equals operator with primary keys. You can also use the \"WHERE\" statement to specify that only rows with column values statisfying a certain condition, should be returned. The \"GROUP BY\" statement will group rows together that have equal column values for whatever columns follows the statement. The \"HAVING\" statement will return groups that statisfy whatever condition follows the statement. Any column(s) being returned from grouped rows must either be an aggregate function, (AVG, MAX, COUNT, SUM, ...) of a column, or the column(s) that the data was grouped by. To sort the returned data you can use the \"ORDER BY\" command which will order the data by whatever aggregate function or column follows the statement. The \"DESC\" statement will sort in descending order and the \"ASC\" statement will sort in ascending order. Finally, you can use the \"LIMIT\" statement to return a certain number of rows. When \"\" is used in an SQL statement every column is returned. For example, SELECT FROM table WHERE attribute = 1, will select every column from rows with the attribute column equal to 1.\n\nShow the ids of the employees who don't authorize destruction for any document.\n" }, { "from": "gpt", "value": "SELECT employee_id FROM Employees EXCEPT SELECT Destruction_Authorised_by_Employee_ID FROM Documents_to_be_destroyed" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task the focus is on physical knowledge about the world. Given the provided goal task in the input, describe a process that would lead to the asked outcome. This process often involves physical motions with objects, such as moving them, arranging them in a certain way, mixing them, shaking them, etc. \nPart 2. Example\nHow do you remove keys from a computer keyboard for cleaning?\nAnswer: Place the tip of a knife under the corner of a key and gently twist to pop it off.\nExplanation: The process of removing keys from a keyboard for cleaning is descriptive and logical.\nPart 3. Exercise\nTo tidy up the pancake making process\nAnswer:" }, { "from": "gpt", "value": "Put the pancake mix in a clean ketchup bottle." } ]
[ { "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: identity-attack and non-identity-attack. Identity attack refers to anything rude or disrespectful about someone's identity, including appearance, race, gender, and sexual orientation.\nQ: Comment: There are no Palestinians. There are only Jew hating Arabs that have no country because the other Arabs don't want them. Supporting them in the west are addle minded anti-semites like yourself.\nA: " }, { "from": "gpt", "value": "Identity-attack" } ]
[ { "from": "human", "value": "Detailed Instructions: 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'.\nSee one example below:\nProblem: What country has borders with Libya, Sudan and Israel?\nSolution: location\nExplanation: This question is about a physical place, so is classified as 'location'\n\nProblem: Who played the role of Becky Sharp in the 2004 film 'Vanity Fair'?\nSolution:" }, { "from": "gpt", "value": "film" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you need to replace a letter in the sentence with another given letter.\nPROBLEM: Sentence: 'the person rides down the path atop the pink skateboard'. Replace the letter 'e' with 'c' in the sentence.\n\nSOLUTION: thc pcrson ridcs down thc path atop thc pink skatcboard\n\nPROBLEM: Sentence: 'a group of people on a beach flying a kite'. Replace the letter 'p' with 'i' in the sentence.\n\nSOLUTION: a groui of ieoile on a beach flying a kite\n\nPROBLEM: Sentence: 'a brown door that says gentlemen and a toilet'. Replace the letter 'o' with 'f' in the sentence.\n\nSOLUTION:" }, { "from": "gpt", "value": "a brfwn dffr that says gentlemen and a tfilet\n\n" } ]
[ { "from": "human", "value": "Definition: In this task, you need to count the number of words in a sentence that contain the given letter\nInput: Sentence: 'a black and white cat staring at a phone on a bed'. How many words contain the letter 'o' in the sentence.\nOutput:" }, { "from": "gpt", "value": "2" } ]
[ { "from": "human", "value": "The input is a tweet which can be classified as Hate Speech, Offensive or Normal. Given such a tweet, output the class the tweet belongs to. Hate Speech will contain threatening language towards the community targeted. Offensive language will contain abusive or discriminatory language towards the community targeted.\n\nExample input: cowardly actions by the pussy brits men let their women be gangraped by moslim animals should change countrys name to cuckland\nExample output: Hate Speech\nExample explanation: This tweet targets Muslim community in a violent context. Hence this is Hate Speech.\nQ: u can be a sand nigger and a kike lol u do not know what either of those terms mean apparently\nA:" }, { "from": "gpt", "value": "Hate Speech" } ]
[ { "from": "human", "value": "Your task is to generate the next utterance in a given dialogue. You will be given a few sentences describing the personality of the person who is making the dialogue, and a history of the dialogue after that. Each line in the history is said by one of the two participants in the conversation.\nQ: Personality: I listen to techno music, exclusively.\nI'm an anime fan.\nMy job involves building drones.\nMy wardrobe is all band tees.\nChat history: -Hello! What is your favorite type of food?\n -Hi there, I mainly like food from food trucks I go to at concerts.\n -Oh delicious! Mexican food is my favorite, but I cannot stand seafood.\n -Cool! I had great mexican at a techno music fest one time. Techno all the way!\n -My mother taught piano, so I must confess that classical is my preference.\n -Oh no! I only listen to techno. Got a whole wardrobe full of techno band tees.\n -Cool! I think I will try listening to techno soon, it sounds fun!\n -You should. What else do you enjoy?\n -Hunting is a hobby of mine, makes sense as I'm from the south. You?\n -I build drones for a living, and a lot of people use those in hunting!\n -Cool! I've never tried using a drone, that sounds fun!\n -You should! Do you like Anime?\n -I do, I love Anime! Have you seen Yuri!! on ice!?\nA: " }, { "from": "gpt", "value": "No! But I'd love to!" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them.\n\nContext Word: cucumber mojito. \nQuestion: PersonX wanted to taste the cucumber mojito that PersonY made but it was all gone. _ was sad. \nAnswer: PersonX\n" }, { "from": "gpt", "value": "PersonX wanted to taste the cucumber mojito that PersonY made but it was all gone. _ was indifferent." } ]
[ { "from": "human", "value": "In this task, you're given a context, a question, three options, and an answer. Your task is to classify whether the given answer is correct or not by providing 'Yes' or 'No', based on the context with commonsense reasoning about social situations.\n\n[Q]: Context: Since Sydney's parents were negligent and abusive, Sydney lived with Carson's parents. \n Question: How would Carson feel as a result? \n Options: (A) angry with their parents (B) disgusted with Sydney (C) protective of Sydney \n Answer: C\n[A]: No\n\n\n[Q]: Context: Robin was an expert on the subject of cats, so Riley picked Robin's brain. \n Question: Why would Riley decide to do this? \n Options: (A) buy a cat from Robin (B) become allergic to cats (C) get some information about cats \n Answer: C\n[A]: Yes\n\n\n[Q]: Context: Skylar tilted Kendall's head back to whisper the secret. \n Question: What will Kendall want to do next? \n Options: (A) Ignore Skylar (B) Run away from Skylar (C) Watch for Skylar's response \n Answer: B\n[A]:" }, { "from": "gpt", "value": "No\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 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.\n\n\" I felt the blast.\nOutput:" }, { "from": "gpt", "value": "Singular" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Given an Amazon review, indicate whether it is a 'Positive Review' or 'Negative Review'.\n\nThe New Trent Airbender 1.0 Wireless Bluetooth Clamshell IPad Keyboard Case is very nice. The first thing I want to note is that the construction feels really well put together when the IPad was connected. The set up was super easy just charge and then pair with Bluetooth. The keyboard is very responsive and just the right size, and rotating the Ipad is very easily done. I am very impressed with the quality of the New Trent Keyboard and highly recommend this product to anyone that is looking for a great keyboard and case combo. I have bought other products from New Trent and have to say they make some of the highest quality products for a very reasonable price.\n" }, { "from": "gpt", "value": "Positive Review" } ]
[ { "from": "human", "value": "In this task you're given a question and you have to paraphrase the question to create the output question while retaining the meaning of the original question.\nExample: What can one do after MBBS?\nExample solution: What do i do after my MBBS ?\nExample explanation: In this example both the question ask the same thing about what to do after MBBS hence second question is the correct output \n\nProblem: Is 1080p a Blu-ray?\n" }, { "from": "gpt", "value": "Solution: Should I bother buying blu-ray discs today, or should I just go with 1080p downloads?" } ]
[ { "from": "human", "value": "In this task, you're given an input that contains two words, and your task is to predict the correct preposition that connects these two words. Predict the preposition that explicitly conveys both words' meaning, e.g., Word1: king \n Word2: fort: \"king of fort\". Possible prepositions are: \"of\", \"on\", \"in\", \"for\", \"from\", \"about\", and \"with\".\n\nWord1: relief \n Word2: earthquake" }, { "from": "gpt", "value": "from" } ]
[ { "from": "human", "value": "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.\nExample: Sentence1: Rick grew up in a troubled household. Sentence2: He never found good support in family, and turned to gangs. Sentence3: It wasn't long before Rick got shot in a robbery. Sentence4: He is happy now.\nExample solution: 4, The incident caused him to turn a new leaf.\nExample explanation: As mentioned in fourth sentence, he is happy now; so, the incident turned a new leaf to Rick's life.\n\nProblem: Sentence1: Sam hopped into his mail truck and drove off. Sentence2: He drove so fast he didn't see a pothole in the road. Sentence3: The truck bounced hard when he hit the pothole. Sentence4: Sam's head hit the steering wheel.\n" }, { "from": "gpt", "value": "Solution: 2, He was trying to do his route fast to get home early today." } ]
[ { "from": "human", "value": "In this task, you need to answer the given multiple-choice question on the general math. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.\n\nProblem: drum x is 1 / 2 full of oil and drum y , which has twice the capacity of drum x , is 2 / 5 full of oil . if all of the oil in drum x is poured into drum y , then drum y will be filled to what capacity ? \nOptions: a ) 4 / 5 , b ) 8 / 15 , c ) 11 / 15 , d ) 9 / 20 , e ) 13 / 20" }, { "from": "gpt", "value": "e" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou are provided with an \"Event\", \"Intent\" and \"XEmotion\" (PersonX's reactions for the given \"Event\"). Indicate PersonY's reaction (person feels) at the end of this event. Provide one reaction for PersonY. If there's nothing that can be implied, respond as None\n\nEvent:PersonX gives PersonY the message. Intent: 1) to be forgiven. XEmotion: 1) forgiven\nOutput:" }, { "from": "gpt", "value": "really nothing at all" } ]
[ { "from": "human", "value": "Instructions: In this task, a passage will be given and the goal is to identify an event from the passage. An event is defined as a single word representing something that happened, is happening, or may happen. An event can be factual or hypothetical, positive or negative, certain or uncertain. While most events are based on verbs, an event can also be based on a noun (ex. storm, snow, rainfall) or a copula verb (is, was, been, etc.). The event must not be a pronoun or an adjective. For noun events with multiple words, use the last word in the phrase as event.\nInput: Passage: Much of the bickering is over Iraq, which has caused sparring between the two political parties and among factions within them. The Republicans dominate the Senate and House of Representatives.\nOutput:" }, { "from": "gpt", "value": "bickering" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Read the given text and if it has abusive content then indicate via \"yes\". Otherwise indicate via\"no\". \nWe consider the content to be abusive if it contains any of the following instances: (1) Identity Directed Abuse (e.g., Content which contains a negative statement made against an identity. An identity is a social category that relates to a fundamental aspect of individuals community, socio-demographics, position or self-representation) (2) Affiliation Directed Abuse (e.g., Content which express negativity against an affiliation. We define affiliation as a (more or less) voluntary association with a collective. Affiliations include but are not limited to: memberships (e.g. Trade unions), party memberships (e.g. Republicans), political affiliations (e.g. Right-wing people) and occupations (e.g. Doctors).) (3) Person Directed Abuse (e.g., Content which directs negativity against an identifiable person, who is either part of the conversation thread or is named. Person-directed abuse includes serious character based attacks, such as accusing the person of lying, as well as aggression, insults and menacing language.) and (4) Counter Speech (e.g., Content which challenges, condemns or calls out the abusive language of others.). Note that URLs in the text have been replaced with [Link].\n\n[Comedy podcast.]\n" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you need to answer the given multiple-choice question on geometry. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.\n\nProblem: in triangle pqr , the angle q = 90 degree , pq = 4 cm , qr = 8 cm . x is a variable point on pq . the line through x parallel to qr , intersects pr at y and the line through y , parallel to pq , intersects qr at z . find the least possible length of xz \nOptions: a ) 1.2 cm , b ) 2.4 cm , c ) 4.8 cm , d ) 2.16 cm , e ) 3.2 cm\n" }, { "from": "gpt", "value": "e" } ]
[ { "from": "human", "value": "In this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story incoherent / implausible by indicating 1 or 2 in the output. If both sentences are plausible, pick the one that makes less sense.\n--------\nQuestion: Beginning: Francis wanted to visit a national park. Middle 1: Francis decided to plan a trip. Middle 2: Francis decided not to take a trip. Ending: She saw such amazing scenery and was so happy she had made the hike.\n\nAnswer: 2\n\n\nQuestion: Beginning: Rex hasn't left his tiny apartment all day. Middle 1: Rex reluctantly went over to his friend's house. Middle 2: Rex reluctantly invited a friend over to his house. Ending: Still he is glad that he left his apartment to see a friend.\n\nAnswer: 2\n\n\nQuestion: Beginning: John loves to eat at buffets. Middle 1: John's favorite buffet went out of business. Middle 2: John's favorite buffet was still in business. Ending: John was sad to hear the news.\n\nAnswer:" }, { "from": "gpt", "value": "2\n\n\n" } ]
[ { "from": "human", "value": "Given a premise and two alternatives, choose the alternative that is a more plausible cause or effect of the situation described by the premise. The input format is \"premise\n(1)alternative_1(2)alternative_2\", the output should either be \"1\" or \"2\" based on your judgment.\n\nExample Input: The businessman's credit card got declined.\n(1)He wrote an IOU.(2)He paid with cash.\nExample Output: 2\n\nExample Input: The waistband on my pants was loose.\n(1)I put on a belt.(2)I put on a hat.\nExample Output: 1\n\nExample Input: I hung the wet linen on the outdoor clothesline.\n(1)The linen dried.(2)The linen stained.\nExample Output:" }, { "from": "gpt", "value": "1\n\n" } ]
[ { "from": "human", "value": "Teacher: In this task, you are given a text which is the body of a document. Your job is to classify the topic of the document into these categories: 1)Company, 2)Educational Institution, 3)Artist, 4)Athlete, 5)Office Holder, 6)Mean of transportation, 7)Building, 8)Natural place, 9)Village, 10)Animal, 11)Plant, 12)Album, 13)Film, 14)Written work. Your output should be the category number. Don't generate anything apart from numbers 1-14.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nText: Abbott of Farnham E D Abbott Limited was a British coachbuilding business based in Farnham Surrey trading under that name from 1929. A major part of their output was under sub-contract to motor vehicle manufacturers. Their business closed in 1972.\nSolution: 1\nReason: Here, the given text is about a British coachbuilding business company. Hence, it is a correct answer.\n\nNow, solve this instance: Text: Dangerous Angels is a young adult fiction series by Francesca Lia Block. It consists of seven novels: Weetzie Bat Witch Baby Cherokee Bat and the Goat Guys Missing Angel Juan Baby Be-Bop Necklace of Kisses and Pink Smog: Becoming Weetzie Bat. The stories are about Weetzie Bat and her friends and family's lives in Los Angeles including witches genies and ghosts on their journeys to find acceptance love and a connection.\nStudent:" }, { "from": "gpt", "value": "14" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. You need to create a question containing a blank (_), based on the given context word. Your question must contain two persons --PersonX and PersonY. The expected answer to your question must be PersonX. PersonX and PersonY should not be equally likely to fill the blank. 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 question. Avoid repeating the same style, pattern, or phrases in each question, try to increase diversity by varying sentence structure, blank placement, etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Person X and Person Y have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.\n\nContext Word: upsell.\n" }, { "from": "gpt", "value": "In an effort to increase commissions, PersonX pushed PersonY hard to buy the addon products that _ was trying to upsell." } ]
[ { "from": "human", "value": "TASK DEFINITION: You are given a short poem which is written by a kid. Your task is to predict if the kid is in elementary school or high school. Anyone who is from grade 1st to 6th-grade will be considered as in elementary school, and 7th to 12th-grade kids will be considered as in high school. There are only two possible outputs, i.e., elementary and high. All inputs have at least one output and it cannot have both categories at a time.\nPROBLEM: where be your homework dear i could n't finish it i fear why ever not my child come here and tell me now well i could n't do my homework last night because alien stole my pencil and fly out of sight i grab my super rocket blaster and blast after them a whole lot faster soon i pass the moon and it really be make of cheese you know i be so hungry i grab a few piece but when i be n't look i crash into venus i try to start my engine but they just would n't start so i take them off and leap with all my heart i fly like a bird offto the planet mar i land with a thump beside my pencil on a hump but then an alien huge and tall throw me off the planet and i start to fall i finally hit the ground i do n't die when all of a sudden my pencil fell and hit me in the eye i look around and saw i be on the school grass that be when i realize i be very late for class that 's what happen it sure be fun and that be why my homework be not do\n\nSOLUTION: elementary\n\nPROBLEM: tough a nail mean like a tornado black a night and orngea a a orngea fast a wind smart a rob m. and stupid a a bum\n\nSOLUTION: elementary\n\nPROBLEM: the sun shine upon the fluffy white cloud the morning dead with silence i awake and wipe my moist head bring down my hand all sweaty i sit up and look out my window the flower be still sleep the dew shine from the firery sun shin upon them morning\n\nSOLUTION:" }, { "from": "gpt", "value": "high\n\n" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nYou are asked to create a question containing a blank (_), based on the given context word. Your question must contain two related but different objects; for example \"trophy\" and \"suitcase\". The expected answer to your question must be one of the objects present in the sentence. The expected answer must not be associated with any specific word in the question; instead it should depend on the context present in the question. The expected answer should not be equally likely to fill the blank. For your question, there should be a agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals or proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style, pattern or phrases in each question, try to increase diversity by varying sentence structure, blank placement etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Object X and Y have the same number e.g. when ObjectX is singular, Object Y must be singular, too. The two objects (Object X & Object Y) should be used ONCE in your question. Here is a list of attributes and associated pair of contrastive words which may be used to create a valid question using the objects. You can use either of the contrastive words, but not both. You should think about more such attributes and associated words and use them in your question.\n\| Attribute \| triggerword \| contrastive triggerword \| \n\| age \| old \| new \| \n\| altitude \| low \| high \|\n\| area \| small \| vast \| \n\| brightness \| dark \| light \| \n\| clarity \| obscure \| clear \| \n\| cleanness \| dirty \| clean \| \n\| complexity \| simple \| complex \| \n\| cost \| cheap \| expensive \|\n\| density \| sparse \| dense \|\n\| depth \| shallow \| deep \|\n\| distance \| near \| far \| \n\| electric conductivity \| low \| high \|\n\| flexibility \| rigid \| flexible \|\n\| granularity \| fine \| coarse \| \n\| hardness \| soft \| hard \| \n\| length \| short \| long \| \n\| magnitude \| small \| large \| \n\| mass \| small \| large \| \n\| odor \| weak \| strong \| \n\| pressure \| low \| high \| \n\| resistance \| low \| high \| \n\| shape \| round \| sharp \|\n\| shape \| flat \| spiky \|\n\| size \| small \| large \| \n\| sound \| quiet \| loud \| \n\| sound pitch \| low \| high \| \n\| speed \| slow \| fast \| \n\| stability \| unstable \| stable \| \n\| strength \| weak \| strong \| \n\| temperature \| low \| high \| \n\| texture \| smooth \| rough \| \n\| thermal conductivity \| low \| high \|\n\| thickness \| thin \| thick \| \n\| volume \| small \| large \|\n\| weight \| light \| heavy \| \n\| width \| narrow \| wide \| \n\| location \| in \| out \|\n\| location \| up \| down \|\n\| location \| above \| below \|\n\| location \| on \| off \|\n\| location \| to \| from \|\n\nExample: Context word: fit.\nOutput: The trophy doesn't fit into the brown suitcase because _ is too large.\nThe question is about two related but different objects (i) \"trophy\" and (ii) \"suitcase\". The quesion contains exactly one blank (_). The expected answer is \"trophy\" which is one of the objects.\n\nNew input case for you: Context Word: warts.\nOutput:" }, { "from": "gpt", "value": "The new cream didn't remove the warts like the last lotion, because the _ was not powerful enough." } ]
[ { "from": "human", "value": "In this task, you are given two sets, and a question. You need to find whether an element is at the intersection of two given sets. A Set is shown by two curly braces and comma-separated numbers inside, like {1, 2, 3}. The intersection of two given sets is the largest set which contains all the elements that are common to both sets. An element is at the intersection of two given sets, A and B, if common to both A and B. Classify your answers into 'Yes' or 'No'.\n--------\nQuestion: Set1: '{7}', Set2: '{10, 15}'. Is the element '15' in the intersection of Set1 and Set2 ?\n\nAnswer: No\n\n\nQuestion: Set1: '{4, 6, 12, 13, 20}', Set2: '{2, 5, 8, 12, 13, 17, 19, 20}'. Is the element '2' in the intersection of Set1 and Set2 ?\n\nAnswer: No\n\n\nQuestion: Set1: '{4, 9, 11, 17, 20}', Set2: '{9, 16, 17, 18, 19}'. Is the element '20' in the intersection of Set1 and Set2 ?\n\nAnswer:" }, { "from": "gpt", "value": "No\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 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.\n\nSentence 1: The name of film that polyester fibers form is mylar. Sentence 2: Mylar® is a trademark of DuPont for its brand of polyester thick film.\nOutput:" }, { "from": "gpt", "value": "entails" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task you are given a small conversation between two persons and 4 options on how the conversation should continue. Your job is to choose the most reasonable option. The conversation and the options are separated by a newline character. Each dialogue in the conversation are separated by a comma. F and M indicate female and male, respectively.\nPart 2. Example\nM: Excuse me. How much is this suit? ,F: It's on sale today for $750. It's normally $900. ,M: Wow, that is pretty expensive! I was thinking that it might be 4 or 500. ,F: This material is imported from Italy. It's the finest in the world, and if you bought a suit made of this material at many department stores, you would pay about $2000. ,M: Uh-hah. But isn't that the point of coming to a market like this, to get a discount compared to the expensive department stores? Besides I saw a suit just like this one a few stalls down, and they were selling it for $600. I still thought that it was too expensive. ,F: It's possible that the suit you saw was the same color is this one but made of a different material. Unfortunately, our prices are final, and we think there are the lowest anywhere in the city.\n(A) M: Okay, I'll buy it at the price you want. Here, it's $600. (B) M: Just a minute! I do not quite follow what you are saying, would you mind repeating that? (C) M: Although the material is imported from France, it is not worth the $750 you want. (D) M: You want $900 for the suit? It's too expensive!\nAnswer: B\nExplanation: Options (A) and (B) are not corrct because the suit's price is 900. Option (C) isn't correct because the material was imported from italy.\nPart 3. Exercise\nM: Mother's birthday is getting close. Have you thought about what to buy for her this year? ,F: Oh, I totally forgot. It's already May tenth. Her birthday is the day after tomorrow, right? ,M: Yes, I will get mom a beautiful dress. It will make her look younger. What do you want to buy? ,F: Since you will buy her a dress, I'll buy her something else. What do you think of a pair of shoes? ,M: Do you know what size she wears? It may not fit her if she doesn't try them on first. ,F: You're right. Do you have any suggestions? ,M: Well, she saw a handbag when I was shopping with her last week. She seemed to like it very much. ,F: Why didn't she buy it? ,M: She couldn't accept the price, but she really liked it. ,F: How about going downtown tomorrow morning? We can get the present for her there. ,M: OK.\n(A) F: And then I'll buy the beautiful handbag for her birthday. I believe she'll love it! (B) F: Since you are going to buy the handbag for mom's birthday, I'll buy the shoes for her. (C) F: I am sorry. You spoke so rapidly that I did not catch the meaning of what you said. Could you repeat that? (D) F: Let me buy the handbag for you tomorrow as your birthday present, my son.\nAnswer:" }, { "from": "gpt", "value": "A" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to write a single word that describes the genre that the two sentences belong to, such as face-to-face, government, letters, 9/11, slate, telephone, travel, verbatim, oup, fiction.\nProblem:Sentence 1: Drinking patterns and problems and drinking in the an analysis of injury by cause among casualty. Sentence 2: Drinking problems have negative effects.\nSolution:" }, { "from": "gpt", "value": "government" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a question. You have to answer the question based on your information.\nQ: Who was born first John Wellborn Root or Daniel Hudson Burnham?\nA:" }, { "from": "gpt", "value": "Daniel Hudson Burnham" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you're given a context passage. Your job is to generate relevant questions that can be answered by directly referring to the passage.\n\nTracy slept awkwardly on their new bed and was having some pain, so Tracy cracked her neck.\nSolution: What did Tracy do with her neck?\nWhy? The question asked is relevant and can be directly answered by referring to the phrase \"so Tracy cracked her neck\" from the passage.\n\nNew input: Quinn earned Ash's income because he was a very good friend.\nSolution:" }, { "from": "gpt", "value": "How would you describe Quinn?" } ]
[ { "from": "human", "value": "In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to generate a natural language interpretation of the given command. \n Here are the definitions of logical operators: \n 1. count: returns the number of rows in the view \n 2. only: returns whether there is exactly one row in the view \n 3. hop: returns the value under the header column of the row \n 4. and: returns the boolean operation result of two arguments \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column \n 6. nth max/nth min: returns the n-th max/n-th min of the values under the header column \n 7. argmax/argmin: returns the row with the max/min value in header column \n 8. nth argmax/nth argmin: returns the row with the n-th max/min value in header column \n 9. eq/not eq: returns if the two arguments are equal \n 10. round eq: returns if the two arguments are roughly equal under certain tolerance \n 11. greater/less: returns if argument 1 is greater/less than argument 2 \n 12. diff: returns the difference between two arguments \n 13. filter eq/not eq: returns the subview whose values under the header column is equal/not equal to argument 3 \n 14. filter greater/less: returns the subview whose values under the header column is greater/less than argument 3 \n 15. filter greater eq /less eq: returns the subview whose values under the header column is greater/less or equal than argument 3 \n 16. filter all: returns the view itself for the case of describing the whole table \n 17. all eq/not eq: returns whether all the values under the header column are equal/not equal to argument 3 \n 18. all greater/less: returns whether all the values under the header column are greater/less than argument 3 \n 19. all greater eq/less eq: returns whether all the values under the header column are greater/less or equal to argument 3 \n 20. most eq/not eq: returns whether most of the values under the header column are equal/not equal to argument 3 \n 21. most greater/less: returns whether most of the values under the header column are greater/less than argument 3 \n 22. most greater eq/less eq: returns whether most of the values under the header column are greater/less or equal to argument 3\nOne example: eq { hop { nth_argmax { all_rows ; attendance ; 3 } ; competition } ; danish superliga 2005 - 06 } = true\nSolution is here: select the row whose attendance record of all rows is 3rd maximum. the competition record of this row is danish superliga 2005-06.\nExplanation: Here, the generated sentence interprets given logical form correctly that 3rd maximum should be selected from given table rows.\n\nNow, solve this: eq { hop { nth_argmax { all_rows ; location attendance ; 2 } ; date } ; january 12 } = true\nSolution:" }, { "from": "gpt", "value": "select the row whose location attendance record of all rows is 2nd maximum . the date record of this row is january 12 ." } ]
[ { "from": "human", "value": "Detailed Instructions: Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].\nSee one example below:\nProblem: ['hey', 'everybody', 'ivan', 'from', 'weights', 'and', 'biases', 'here', 'in', 'this', 'video', \"i'd\"]\nSolution: ['CASE_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'CASE_DIFF', 'UNKNOWN_TYPE_DIFF', 'CASE_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF']\nExplanation: This sentence is a good example since the input stream is a grammatically incorrect statement and the output labels correctly classify the words that were incorrect.\n\nProblem: ['things', 'are', 'starting', 'to', 'get', 'interesting', 'in', 'the', 'first', 'video', 'we', 'set', 'up', 'a', 'spacetime', 'diagram', 'for', 'my', 'frame', 'of', 'reference', 'that', 'started', 'to', 'plot', 'things', 'paths', 'in', 'that', 'space-time', 'diagram', 'and', 'then', 'we', 'thought', 'about', 'our', 'friend', 'Sally', 'who', 'write', 'at', 'time', 'equals', 'zero', 'is', 'it', 'x', 'equals', 'zero', 'but', \"she's\", 'passing', 'me', 'up', 'at', 'a', 'relative', 'velocity', 'of', 'half', 'the', 'speed', 'of', 'light', 'in', 'the', 'positive', 'x-direction', 'so', 'after', 'one', 'second', 'she', 'has', 'gone', 'one', 'and', 'a', 'half', 'times', 'ten', 'to', 'the', 'eighth', 'meters', 'and', 'the', 'positive', 'x-direction', 'after', 'two', 'seconds', \"she's\", 'gone', 'three', 'times', 'ten', 'to', 'the']\nSolution:" }, { "from": "gpt", "value": "['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'INTRAWORD_PUNC_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'DIGIT_DIFF', 'NO_DIFF', 'NO_DIFF', 'DIGIT_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'DIGIT_DIFF', 'NO_DIFF', 'NO_DIFF']" } ]
[ { "from": "human", "value": "In this task, you are given a statement spoken by a politician in natural language. Your task is to generate the subject of the discussion for the given statement. The subject generated is not necessarily a part of the given input. Your answer should contain one or more words.\n\nQ: Marco Rubio opposes extending unemployment benefits.\n\nA: economy\n**\nQ: Says Gary Farmers claim that he received an A from the NRA is an absolute lie.\n\nA: guns\n\nQ: Ebola is incredibly contagious, very transmissible and easy to catch.\n\nA:" }, { "from": "gpt", "value": "ebola\n**\n" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given product reviews about dvds. The goal is to classify the review as \"POS\" if the overall sentiment of the review is positive(the reviewer is satisfied) or as \"NEG\" if the overall sentiment of the review is negative(the reviewer is not satisfied).\nExample: My Kids Love It . My 2 & 3 year old love this movie. They love to dance to the music. Garfield is so entertaining. This was a great buy.\nOutput: POS\nThe overall sentiment of the review is positive as the reviewer refers to the dvd with positive expressions such as 'love it', 'entertaining', 'great' etc. Hence, the label is 'POS'.\n\nNew input case for you: TRASH! Had to choose at least 1 star but it is ZERO ! . Bought this awhile back and forgot I had it. Watched it and then I rememebered how AWFUL it was. Was about to throw it out and then thought maybe I could reuse the case?\nOutput:" }, { "from": "gpt", "value": "NEG" } ]
[ { "from": "human", "value": "Instructions: In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis. It makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis. It makes you much more likely to believe the hypothesis is true. Your task is to output 'strengthener' or 'weakener' if the update strengths or weakens the hypothesis, respectively.\nInput: Premise: PersonX talks out of turn\nHypothesis: PersonX is seen as assertive\nUpdate: PersonX is trying to be the leader of the project\nOutput:" }, { "from": "gpt", "value": "strengthener" } ]
[ { "from": "human", "value": "In this task, you need to write a topic word from the given fact. The topic word must have at least one word overlap with the given fact. The topic word often involves adding a new word from a related concept. In your topic word, use at least one word from the given fact. Topic words with two or more words work best.\n\nInput: Consider Input: Fact: Excretion is the process of removing wastes and excess water from the body.\n\nOutput: body waste.\n\n\nInput: Consider Input: Fact: Condoms can break; Condoms can be used incorrectly.\n\nOutput: condom birth control.\n\n\nInput: Consider Input: Fact: a thermometer is used to measure temperature.\n\n" }, { "from": "gpt", "value": "Output: Temperature derermine weather.\n\n\n" } ]
[ { "from": "human", "value": "Teacher:In this task you will be given a list of dictionaries. A dictionary is a set of key-value pairs, where each key is unique and has a value associated with that key. You should sort the list of dictionaries from smallest to largest by their 'first' key. If there is two dictionaries with the same 'first' value then sort them by their 'second' key. Negative numbers should come before positive numbers.\nTeacher: Now, understand the problem? Solve this instance: [{'first': -86, 'second': 96}, {'first': 89, 'second': -93}, {'first': 81, 'second': -7}, {'first': -33, 'second': -88}, {'first': 59, 'second': -70}, {'first': 42, 'second': 83}, {'first': -61, 'second': 82}, {'first': 80, 'second': -46}, {'first': 84, 'second': -26}, {'first': 13, 'second': 54}]\nStudent:" }, { "from": "gpt", "value": "[{'first': -86, 'second': 96}, {'first': -61, 'second': 82}, {'first': -33, 'second': -88}, {'first': 13, 'second': 54}, {'first': 42, 'second': 83}, {'first': 59, 'second': -70}, {'first': 80, 'second': -46}, {'first': 81, 'second': -7}, {'first': 84, 'second': -26}, {'first': 89, 'second': -93}]" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a 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\nthank you, can you tell me more about the history here?\nOutput:" }, { "from": "gpt", "value": "user" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a statement about date and time, state whether the statement is true or false. The number of date/time operands in the statement ranges between 2 and 3. Let's say the values are denoted by t1, t2 and t3. The statements follow one of the following ten templates: 't1 occurs before t2, t1 doesn't occur before t2, t1 occurs after t2, t1 doesn't occur after t2, t1 occurs between t2 and t3, t1 doesn't occur between t2 and t3, t1 occured before t2 but after t3, t1 occured after t2 but before t3, t1 didn't occur before t2 but after t3, t1 didn't occur after t2 but before t3'. The output should be either 'True' or 'False'.\nQ: 2:13:02 PM occurs between 05:24:40 PM and 09:28:18\nA:" }, { "from": "gpt", "value": "True" } ]
[ { "from": "human", "value": "In this task, you need to count the number of words in a sentence that end with the given letter. Answer with numbers and not words.\nQ: Sentence: 'some long benches dry trees and a lamp post'. How many words end with the letter 'e' in the sentence.\nA: " }, { "from": "gpt", "value": "1" } ]
[ { "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.\nQ: [[-21, 42, -42, -14, -13], [-49, 3, -17], [-38, -37, 14, 25], [21, -44, 48, -35, -26]]\nA: " }, { "from": "gpt", "value": "[6742008, 2499, 492100, -40360320]" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. This is a paraphrasing task. In this task, you're given a sentence and your task is to generate another sentence which express same meaning as the input using different words.\n\nmaybe it is n't a business decision , maybe it 's personal .\n" }, { "from": "gpt", "value": "maybe it 's something personal ." } ]
[ { "from": "human", "value": "In this task the focus is on physical knowledge about the world. Given the provided goal task in the input, describe a process that would lead to the asked outcome. This process often involves physical motions with objects, such as moving them, arranging them in a certain way, mixing them, shaking them, etc. \n\nhow to charge riding mower battery" }, { "from": "gpt", "value": "Make sure the charger is off. Hook-up the positive cable on the charger to the positive terminal on the battery. Hook up the negative cable on the charger to the negative terminal on the battery. Set the charger to the slowest charge rate." } ]
[ { "from": "human", "value": "Given a category and a set of five words, find the word from the set that does not belong (i.e. is the least relevant) with the other words in the category. Words are separated by commas.\n\nExample Input: Category: shady activities \nWords: fudge, banned, brownie, unwarranted, fib\nExample Output: brownie\n\nExample Input: Category: activity \nWords: spend, divide, apple, whittle, fritter\nExample Output: apple\n\nExample Input: Category: emotional display \nWords: social, swoon, love, fawn, deer\nExample Output:" }, { "from": "gpt", "value": "deer\n\n" } ]
[ { "from": "human", "value": "In this task, you're given a question, along with a context passage. The passage will not have a direct answer to the question, but can include some information and a clue for the answer. Assuming you can only obtain information about one entity in the passage, your job is to determine whether information from the passage can be used to answer the question. Indicate your choice as `a` for Yes or `b` for No.\n\nInput: Consider Input: Question: Which country did Innocent Oula return to after Somalia? Passage:Innocent Oula joined the National Resistance Army in 1986 at the rank of captain. He rose through the ranks and has served as a member of UPDF delegation during the ill-fated Juba Peace Talks, at the rank of lieutenant colonel. At the level of colonel, in 2009, he served at the director of training for the UPDF 2nd Division, based at Mbarara, in Western Uganda. From 2010 until 2011, he served as the Chief of Staff of AMISOM, based in Mogadishu, Somalia. On his return from Somalia, he was posted to the 4th UPDF Division headquarters in Gulu, as the commanding officer. He later was appointed chief of personnel and administration in the UPDF, based at the Mbuya Barracks. In January 2014, he was elected to the Parliament of Uganda, as a UPDF representative. In November 2014, he was promoted to the rank of brigadier, along with more than 1,300 UPDF officers who received promotions at the same time.\n\n\nOutput: b\n\n\nInput: Consider Input: Question: What other advertisements did Microsoft release the year it launched The Life? Passage:The Life, also known as We Are ODST is a television and cinema advertisement launched in 2009 by Microsoft to promote the first person shooter in the United States. The 150-second piece follows a young soldier through enlistment, training, and battle as an Orbital Drop Shock Trooper (ODST), analogous to a paratrooper that drops from space to a battlefield. The Life was created by advertising agency T.A.G., an offshoot of McCann Erickson. Production of the commercial itself was handled by production company Morton/Jankel/Zander (MJZ). It was directed by Rupert Sanders, and post-production was conducted by Asylum. It was filmed in Hungary, just outside Budapest in a coal mine and abandoned factories to give the sequence an \"Eastern Bloc\" aesthetic. The commercial and its associated campaign proved hugely successful; on the week of its launch, Halo 3: ODST became the top-selling game for the Xbox 360 worldwide, and over 2.5 million copies were sold within the first few weeks of release. The Life went on to win a number of honours from the advertising and entertainment industries, including two Clio Awards, a London International Advertising Award and several honours from the Cannes Lions International Advertising Festival, the most prestigious awards ceremony in the advertising industry.\n\n\nOutput: a\n\n\nInput: Consider Input: Question: Who founded the largest such car club? Passage:Sonoma Raceway, formerly Sears Point Raceway and Infineon Raceway, is a road course and drag strip located on the landform known as Sears Point in the southern Sonoma Mountains in Sonoma, California, USA. The road course features 12 turns on a hilly course with of total elevation change. It is host to one of only two NASCAR Sprint Cup Series races each year that are run on road courses (the other being Watkins Glen International in Watkins Glen, New York), and one of six national series road course races (Xfinity Series racing at Watkins Glen, Mid-Ohio Sports Car Course and Road America; and the Camping World Truck Series at Canadian Tire Motorsport Park). It is also host to the Verizon IndyCar Series and several other auto races and motorcycle races such as the American Federation of Motorcyclists series. Sonoma Raceway continues to host amateur, or club racing events which may or may not be open to the general public. The largest such car club is the Sports Car Club of America.\n\n\n" }, { "from": "gpt", "value": "Output: b\n\n\n" } ]
[ { "from": "human", "value": "Definition: Write a correct answer for the question. You should reason about prototypical situations and provide the correct answer. Avoid answers that provide incomplete justification for the question.\nInput: name something you might do to win over your in-laws.\nOutput:" }, { "from": "gpt", "value": "cook nice meals" } ]
[ { "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\nLet me give you an example: Beginning: Lauren finished her late night shift at the bar feeling tired. Middle: Lauren took a long hot bath when she got home. Ending: Lauren's husband was glad to see her feeling refreshed.\nThe answer to this example can be: Lauren's husband took a long hot bath when he got home.\nHere is why: If a person takes a bath, another person's tiredness is not reduced.\n\nOK. solve this:\nBeginning: Jack had been experiencing stomach pain all day. Middle: Jack went to hospital in the evening. Ending: Jack was admitted to the hospital and had his appendix removed.\nAnswer:" }, { "from": "gpt", "value": "Jack found relief in the evening." } ]
[ { "from": "human", "value": "Teacher: In this task, you're given the beginning and the middle of a three-part story. Your job is to complete the short story by writing a probable ending. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the ending, and use names instead of pronouns (e.g. he / she) wherever possible.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nBeginning: Helen lived in the state of Washington. Middle: Helen planned to drive to Canada but it started snowing heavily.\nSolution: Helen stayed home instead and planned to go another day.\nReason: Generally, people prefer not to drive in bad weather.\n\nNow, solve this instance: Beginning: My body started to feel weak throughout the week. Middle: I decided to perform in the concert anyhow.\nStudent:" }, { "from": "gpt", "value": "The audience cheered for me." } ]
[ { "from": "human", "value": "In this task, you are given two facts, and a multiple-choice question. Based on the given facts, answer the question with index of the correct option (e.g, \"A\").\n\nExample input: Fact1: a plant requires sunlight to grow, Fact2: Plants to avoid are fast-growing vines that can take over an area in no time., Question: What requires sunlight in order to take over an area? (A) spores (B) fish (C) plants (D) humans (E) pods (F) Oak (G) opossums (H) coral\nExample output: C\nExample explanation: This is a good example. Based on the facts plants require sunlight in order to take over an area.\nQ: Fact1: Spores may be dispersed by moving water, wind, or other organisms., Fact2: Humans are complex organisms., Question: what can disperse spores? (A) alpacas (B) insects (C) humans (D) wind (E) honeybees (F) seeds (G) fungi (H) ferns\nA:" }, { "from": "gpt", "value": "C" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a Reddit post as a text. Your task is to generate a short summary for this text. The summary must include a situation which caused humor. The summary should be one or two sentences long.\nProblem:Text: happened a couple of hours ago. \n\nwas sitting on the couch talking to my wife when my cat came past looking for some affection. \n\ni have had the cat for 16yrs now. 3/4 burmese 1/4 abysinian chocolate short hair. only been with my wife for the past 4 years so the cat is anyways a touch jealous in its behavior. \n\nso when the cat came past it typically ignored my wife and came towards me. \n\ni'm sitting in the corner of the couch. one leg down on the floor, the other kind of curled up with my foot under my butt.\n\nwe have a pile of fluffy blankets on the couch for when my wife gets cold so there's not really much room for the cat to jump up, but i call to it anyway. \n\nthe cat doesn't jump so well anymore. it's old. so there's normally a grab and clamber up...\n\ni dont consider that. \n\ntifu - i call again. \n\nthe cat jumps and i'm just wearing boxer shorts.\n\nthe cat claws to get hold and skewers the head of my penis...and i'm in agony!!\n\nin the process of getting the cat lose i also accidentally belt one of my nuts with my wrist so now the whole area is just in blinding pain...\n\n\ncat runs off to hide and my wife (bless her) is extremely sympathetic, along me how she can help...\n\n\now....\n\n\n \n\nedit: typo\nSolution:" }, { "from": "gpt", "value": "- cats don't give good piercings..." } ]
[ { "from": "human", "value": "Teacher: In this task, you are given two facts, and a multiple-choice question. Based on the given facts, answer the question with index of the correct option (e.g, \"A\").\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nFact1: a plant requires sunlight to grow, Fact2: Plants to avoid are fast-growing vines that can take over an area in no time., Question: What requires sunlight in order to take over an area? (A) spores (B) fish (C) plants (D) humans (E) pods (F) Oak (G) opossums (H) coral\nSolution: C\nReason: This is a good example. Based on the facts plants require sunlight in order to take over an area.\n\nNow, solve this instance: Fact1: Adult sponges are sessile., Fact2: Sessile Attached permanently, immobile., Question: What is true of all adult sponges? (A) they are immobile. (B) at or near the margins (C) They may not survive. (D) water conservation (E) Light passing through water (F) competition (G) To keep their body heat. (H) permineralization\nStudent:" }, { "from": "gpt", "value": "A" } ]
[ { "from": "human", "value": "Q: In this task, you're given reviews from Amazon's products. Your task is to generate the Summary of the review.\nItem didn't arrive. They sent replacement. Now they are saying I didn't RETURN item. How do I return something that didn't arrive?\nA:" }, { "from": "gpt", "value": "Item didn't arrive. They sent replacement. Now they are saying I didn't RETURN item." } ]
[ { "from": "human", "value": "Q: In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write the required POS tag answering the question. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb\nWhat is the part-of-speech tag of the word \"of\" in the following question: Who created this organization that this institute , located in the city of 6,912 residents as of 2010 , is known as the birthplace of ?\nA:" }, { "from": "gpt", "value": "IN" } ]
[ { "from": "human", "value": "In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\n[EX Q]: for the pick records of all rows , most of them are equal to 6 .\n[EX A]: most_eq { all_rows ; pick ; 6 }\n\n[EX Q]: select the rows whose player record fuzzily matches to jo angel ( wa ) . take the matches record of this row . select the rows whose player record fuzzily matches to clarrie grimmett ( vic / sa ) . take the matches record of this row . the first record is greater than the second record .\n[EX A]: greater { hop { filter_eq { all_rows ; player ; jo angel ( wa ) } ; matches } ; hop { filter_eq { all_rows ; player ; clarrie grimmett ( vic / sa ) } ; matches } }\n\n[EX Q]: select the rows whose municipality record fuzzily matches to tecate . take the area ( km2 ) record of this row . select the rows whose municipality record fuzzily matches to tijuana . take the area ( km2 ) record of this row . the first record is greater than the second record .\n[EX A]:" }, { "from": "gpt", "value": "greater { hop { filter_eq { all_rows ; municipality ; tecate } ; area ( km2 ) } ; hop { filter_eq { all_rows ; municipality ; tijuana } ; area ( km2 ) } }\n\n" } ]
[ { "from": "human", "value": "You are given an amazon food product review and its polarity (positive or negative). Your task is to answer \"True\" if the specified sentence and its polarity match; otherwise, answer \"False\".\n\nEx Input:\nTo me this coffee was extremely bitter. I dumped it out and made a different cup. It made me afraid to try other WP coffees but I did like the WP Sumatra Kopi Raya. For reference purposes my in store drink is a Starbucks Americano. My favorite k-cups are: Starbucks French Roast Starbucks Caffe Verona Starbucks Pike Place Roast Green Mountain Xtra Bold Sumatran Reserve Green Mountain Double Black Diamond Green Mountain Revv Green Mountain Dark Magic Other k-cups I've tried: Coffee People Jet Fuel ,Green Mountain Dark Magic Decaf, Emeril Jazzed up Decaf, Starbucks Caffe Verona, Coffee People Black Tiger, Starbucks House Blend, Starbucks Breakfast Blend, Starbucks Sumatra, Wolfgang Puck French Roast, Green Mountain Lake and Lodge, Green Mountain French Roast, Caribou Mahogony, Wolfgang Puck Sumatra Kopi Raya, Emeril Big Easy Bold \n Polarity: Negative\n\nEx Output:\nTrue\n\n\nEx Input:\nServeice delivery with the seller was excellent. The product was not. Will not order again. Bad taste. Iam not sure if it was old or that how it tastes. I throw it right away, i coudl not drink it. \n Polarity: Negative\n\nEx Output:\nTrue\n\n\nEx Input:\nThey have some textured powder stuff on them that makes them taste bad.. bad after taste. I guess it's so they don't stick together. Never again \n Polarity: Negative\n\nEx Output:\n" }, { "from": "gpt", "value": "True\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: You will be given three sentences. Read them, then identify a noun phrase (person, place, or thing) or event that is shared between all three sentences. As the output, write the span of the text corresponding to that phrase in each sentence. Keep the order of the sentences, that is, your answer should look like: 1: a phras from sentence 1e 2: a phras from sentence 2 3: a phrase from sentence 3\nQ: 1: For example , we have gone from 89 cents in our rainy day fund and an $ 8 billion shortfall to now having one of the nation 's strongest state budgets and a nearly $ 2 billion surplus . 2: We've gone from losing 350,000 private-sector jobs to creating about 340,000 new ones . 3: He says Ohio has gone from a budget deficit to surplus , from losing jobs to creating them .\nA:" }, { "from": "gpt", "value": "1: we 2: We've 3: Ohio" } ]
[ { "from": "human", "value": "instruction:\nGiven a 'poster' sentence and a corresponding 'response' (often, from Facebook or Reddit)classify the sentiment of the given response into four categories: 1) Positive, 2) Negative, 3) Neutral, and 4) Mixed if it contains both positive and negative.\nquestion:\nPoster: Isakson Statement on Budget Deal That Avoids Shutdown of Government Responser: Glad we take all our pay on the first, surely they will work it out before then, just in case, we will live on a shoe string this month!\nanswer:\nMixed\n\n\nquestion:\nPoster: IMA BE RAPPING ON THIS RATCHET ASS SKETCH ON MTV Girl Code TONIGHT!! 11PM EST TUNE IN!! Responser: Call of Duty: Advanced Warfare i can FLY: http://youtu.be/bnTqQg5EnEA\nanswer:\nNeutral\n\n\nquestion:\nPoster: Listen to the first two chapters of Odd Interlude at Audible.com http://www.audible.com/mt/SneakPeek_OddInterlude Click 'Like' if you're excited about the launch of the complete audiobook on December 27th ! Responser: As much as I like audio books, I'll always love buying hardcovers.\nanswer:\n" }, { "from": "gpt", "value": "Neutral\n\n\n" } ]
[ { "from": "human", "value": "Teacher: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.\"\nTeacher: Now, understand the problem? Solve this instance: Beginning: Charles wanted to be a successful writer. Middle: Charles worked very hard on his latest book. Ending: He self published the title and then got a call from a publisher.\nStudent:" }, { "from": "gpt", "value": "Charles didn't put much time into the latest book." } ]
[ { "from": "human", "value": "Teacher: In this task, you will be presented with a question, a word, and a POS tag. You have to determine whether the part-of-speech tag of the given word in the question is equal to the given POS tag or not. Give your answer with True or False. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nWho were the builders of the mosque in Herat with fire temples ? \n, Word: Who \n, POS tag: IN\nSolution: False\nReason: This is a good example. POS tag of who should be WP(Wh-pronoun), and not IN(Preposition).\n\nNow, solve this instance: Which awardees alma mater is currently coached by Chuck Martin ? \n, Word: Chuck \n, POS tag: JJ\nStudent:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "You are given a question or fill-in-the-blank question, two answer options (Option1 and Option2) and an Explanation. Your task is to find the correct answer (return the string of the correct option, not option1/2) for the given question from the given options and using explanation.\n\nQuestion: Which two objects likely have the greatest gravitational force between them? \n Option1: Earth and Neptune \n Option2: Jupiter and Neptune \n Explanation: This is because the gravitational force of attraction between the Earth and Sun is stronger when the Earth is closer to the Sun." }, { "from": "gpt", "value": "Jupiter and Neptune" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you're given a context, a sentence, and a character. The sentence describes an action or job of the given character. Also, the context provides more information about the sentence or the character. Your task is to return one of the emotions which are expressed by the Character in the given sentence. For that you can use the Context; however, Context is not provided in all the inputs. Also, in some inputs, there can be zero emotion; for that return 'None'.\n\nContext: None \n Sentence: June fell out of her tree house. \n Character: Her mom\n" }, { "from": "gpt", "value": "None" } ]
[ { "from": "human", "value": "Instructions: In this task, you are given two strings A,B. Find the longer of the two lists, convert it to lowercase, and return all the unique alphabets used in it. The two input strings are never equal.\nInput: GSZETJbkWHEIuRBHALJDEbSAaAIdhLWrX, kFLpxNdkPpraPRBHALJDEbSAaAIhcp\nOutput:" }, { "from": "gpt", "value": "a, b, d, e, g, h, i, j, k, l, r, s, t, u, w, x, z" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given an abstract of article. Your task is to generate title for this article. Preferred titles are under thirty words.\nProblem:Both signal transducer and activator of transcription 3 (STAT3) and SALL4 are important in maintaining the pluripotent and self-renewal state of embryonic stem cells. We hypothesized that STAT3, a latent transcriptional factor, may regulate the gene expression of SALL4. In support of this hypothesis, DNA sequence analysis of the SALL4 gene promoter revealed four putative STAT3-binding sites. Using a SALL4-luciferase reporter gene assay, we found that modulation of the STAT3 activity significantly up-regulated the luciferase activity. By chromatin immunoprecipitation, the segment of the SALL4 promoter showing the highest affinity to STAT3 was localized to -366 to -163, in which there was only one putative STAT3 binding site starting at -199. Site-directed mutagenesis of all four putative STAT3-binding sites in the SALL4 promoter significantly reduced its responsiveness to STAT3, although the most dramatic effect was seen at the binding site starting at -199. We further tested the functional relationship between STAT3 and SALL4 using MDA-MB-231, a breast cell line carrying constitutive SALL4 expression and STAT3 activity. Down-regulation of the STAT3 activity using a dominant-negative construct resulted in a significant decrease in the expression of SALL4. To conclude, our data suggest that STAT3 and SALL4 probably cooperate in both physiological and pathological states.\nSolution:" }, { "from": "gpt", "value": "Signal transducer and activator of transcription 3 is a transcriptional factor regulating the gene expression of SALL4." } ]
[ { "from": "human", "value": "Q: Given a sentence, generate what should be the most likely next statement. The next statement should be reasonable and logically correct.\nHis armed accomplice backs up the stairs. The mastermind\nA:" }, { "from": "gpt", "value": "turns around and climbs the steps to the lobby." } ]
[ { "from": "human", "value": "Given an Amazon review, indicate whether it is a 'Positive Review' or 'Negative Review'.\n\nNo problems, great tablet, long battery life" }, { "from": "gpt", "value": "Positive Review" } ]
[ { "from": "human", "value": "Categorize the comment on the basis of toxicity. If the comment is toxic (harmful, malicious, derogatory, threat, insult, identity attck, etc.) output Yes, otherwise output No.\nOne example: haha you guys are a bunch of losers.\nSolution is here: Yes\nExplanation: The comment here has word 'losers', which is used as an attack on a subject in the comment. Hence, it is a positive example\n\nNow, solve this: The decision to file a Petition to Revoke parole or probation--a PTR--is the parole/probation officer's call. The judge can agree to bail but the parole board has the final call: It can either hold the person in prison pending a parole hearing or agree to release them on bail. Either way, being held in jail shouldn't be a death sentence.\nSolution:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Q: 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.\nSo I stand there on the side of the street, made an eye contact with the cab driver, and raised my hand and waved at him. He gave me a quick flash of his headlights to signal that he saw me, He made his way to the side of the street. So I opened the door and got inside. I said to the driver, \"let's go to the main street, Sooner the better.\" The driver turned on his signal to merge into the traffic. It's weird how some people yield to merging traffic, while others ignore them. I think it must be a personality thing, but it's always safer to yield. No need to drive aggressively. The driver drives at a casually fast pace, weaving in and out of lanes as needed. We got to the main street in about 10 minutes. Guess it's time to pay the man. \"Thanks, driver, for getting here right quick,\" I said. I opened the door and got out.\nA:" }, { "from": "gpt", "value": "Who was in the taxi?" } ]
[ { "from": "human", "value": "Detailed Instructions: You are given a question. You need to detect which category better describes the question. A question belongs to the description category if it asks about description and abstract concepts. Entity questions are about entities such as animals, colors, sports, etc. Abbreviation questions ask about abbreviations and expressions abbreviated. Questions regarding human beings, description of a person, and a group or organization of persons are categorized as Human. Quantity questions are asking about numeric values and Location questions ask about locations, cities, and countries. Answer with \"Description\", \"Entity\", \"Abbreviation\", \"Person\", \"Quantity\", and \"Location\".\nProblem:Who was the Democratic nominee in the American presidential election ?\nSolution:" }, { "from": "gpt", "value": "Person" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given a sentence from the research paper and your task is to classify the given sentence into the following categories: Background (Why is this problem important? What relevant works have been created before? What is still missing in the previous works? What are the high-level research questions? How might this help other research or researchers?), Purpose (What specific things do the researchers want to do? What specific knowledge do the researchers want to gain? What specific hypothesis do the researchers want to test?), Method (How did the researchers do the work or find what they sought? What are the procedures and steps of the research?), or Finding (What did the researchers find out? Did the proposed methods work? Did the thing behave as the researchers expected?). \nTeacher: Now, understand the problem? Solve this instance: destinations , husbandry and costs associated with the care of these animals.\nStudent:" }, { "from": "gpt", "value": "purpose" } ]
[ { "from": "human", "value": "In this task, you're given a review from Amazon's food products. Your task is to generate a short summary of the given review in the input. Note that you don't need to write a complete sentence as a summary.\n\nThis tastes just like Wint-O-Green Life Savers. It's a hard, sweet, crunchy ring, with a minty flavor. That pretty much describes it. It's a crunchy mint shaped like a ring." }, { "from": "gpt", "value": "Tastes Like Wint-O-Green Life Savers" } ]
[ { "from": "human", "value": "In this task you are given a list of triplets of the form [subject, predicate, object] and the output should be a question based on the triplets but with the subject and/or object replaced with blanks (represented using two or more consecutive underscores). Triplet values encompassed in [*] are special tokens that can be replaced with synonyms. The objective is to construct a question in a manner that (a) captures the facts specified in at least one of the triplets, and (b) ideally contains a limited number of blanks such that it is a well-formed question that is easy to answer. A blank can represent a single word or a phrase.\n\n[['Aromi', 'eatType', 'coffee shop'], ['Aromi', 'food', 'Indian'], ['Aromi', 'customer rating', 'average'], ['Aromi', 'area', 'city centre'], ['Aromi', 'familyFriendly', 'no']]\n_____ is a coffee shop which provides _____ food. It has an average customer rating and is located in the city centre. It is not family friendly.\n\n[['SS7', 'NAME', 'Finnskogen']]\n_____ is the location for the _____ stage of the 2007 Rally Norway.\n\n[['The Mill', 'eatType', 'pub'], ['The Mill', 'food', 'Chinese'], ['The Mill', 'priceRange', 'high'], ['The Mill', 'area', 'city centre']]\n" }, { "from": "gpt", "value": "A Chinese pub, _____, is located in the city centre. It is in the high price range.\n\n" } ]

Subsets and Splits

No community queries yet

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