Search is not available for this dataset
conversations
listlengths 2
2
|
|---|
[
{
"from": "human",
"value": "You are given a target race, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.\nOne example: Target: hispanic \nMy professor is a hispanic man. He came here illegally.\nSolution is here: stereotype\nExplanation: This is a stereotype because not every hispanic person has moved to a different country and is undocumented.\n\nNow, solve this: Target: Somalia \nOne of my friends visited Somalia. The volcano erupted and spewed out lava.\nSolution:"
},
{
"from": "gpt",
"value": "unrelated"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: You are given a short paragraph, a question and two choices to answer from. Choose the correct answer based on the paragraph and write the answer(not the key).\nSee one example below:\nProblem: Paragraph: Many of the worlds people live with water scarcity, and that percentage will increase as populations increase and climate changes.\n Question: John's town used to have lots of water, back when there were only a few hundred people. However, now that the town holds several thousand people, the water availability is \n Choices: A)scarce \nB)plentiful\nSolution: scarce\nExplanation: Based on the information given in the paragraph, population growth will make water more scarce, so that is the correct answer.\n\nProblem: Paragraph: If we increase the resistance in a series circuit, by adding more resistors, then the total current decreases.\n Question: Polly was adding resistors to a circuit. Increasing the resistance in this series circuit will cause the total current to \n Choices: A)increase \nB)decrease\nSolution:"
},
{
"from": "gpt",
"value": "increase"
}
] |
[
{
"from": "human",
"value": "In this task, you will be shown a conversation. You need to write a question with three choices for the conversation. Your question should be answerable based on the conversation and only have one correct answer. Note that you don't need to answer your question. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\n\nLet me give you an example: W: The movie next Tuesday has been cancelled due to lack of interest. M: What do you mean? W: Well, by last night only a few tickets has been sold.\nThe answer to this example can be: What can we conclude about the movie? (A) They want to buy the tickets for the movie. (B) The tickets for the movie were sold. (C) The movie will not be shown.\nHere is why: This is a good example. Based on the conversation, the movie has been canceled, and it will not be shown. We could understand that only option (C) is correct. As mentioned in the conversation, only a few tickets have been sold, so option (B) is incorrect. We don't know if they wanted to buy a ticket or not, so option (A) is incorrect as well.\n\nOK. solve this:\nM: How are your home-stay families chosen? W: We have special requirements that our families must meet before they are invited to have our international students. We require that the family lies live within a reasonable distance of the school, have enough living space for the student, and live in a clean, safe and comfortable area. We also work with families who enjoy having international students. We try to match each student with a family as best we can. M: If I stay with a home-stay family, what should I expect? W: The family will treat you as a guest, and you will be expected to obey house rules. All families provide a single or shared room and a choice of meals. In most cases, students will be expected to share the bathroom. Experiences has shown us that living with a family is the most interesting and effective way to learn the language. Remember, your home-stay family will have different customs and habits from what perhaps you are used to. Meals will be prepared by the family. All home-stay families are within 30 minutes, travelling time of the school. The smaller the city, the less time it takes to reach the school.\nAnswer:"
},
{
"from": "gpt",
"value": "What kind of families can be possibly chosen as home-stay families? (A) Good at cooking. (B) Close to the school. (C) With international background."
}
] |
[
{
"from": "human",
"value": "Given a sentence in Somali language, translate the sentence to English language keeping the meaning of the original sentence intact\n\nExample input: Somali sentence: Lionel Messi waa ciyaaryahanka ugu weyn kubadda cagta abid\nExample output: Lionel Messi is the greatest football player of all time\nExample explanation: The output exactly translates the Somali sentence to it's English equivalent. Even though the phrase 'greatest player ever' is translated to 'greatest player of all time', the meaning remains the same.\nQ: Somali sentence: 5 Oo markay aad u afuufaan buunanka wananka geesahooda ah, oo idinku aad maqashaan dhawaaqa buunka, dadka oo dhammu qaylo dheer waa inay ku qayliyaan, oo markaasaa derbiga magaaladu meeshiisa ku dhici doonaa, dadkuna waa inuu nin waluba hortiisa qummaati ugu socdaa.\nA:"
},
{
"from": "gpt",
"value": "5 And it shall come to pass, that when they make a long blast with the ram's horn, and when ye hear the sound of the trumpet, all the people shall shout with a great shout; and the wall of the city shall fall down flat, and the people shall ascend up every man straight before him."
}
] |
[
{
"from": "human",
"value": "In this task, you are given an impractical statement. You are also given three reasons (associated with \"A\", \"B\", \"C\") explaining why this statement doesn't make sense. You must choose the most corresponding reason explaining why this statement doesn't make sense.\n\nHe went to the hospital to withdraw money.\n(A) Hospitals may not have enough cash.\n(B)People do not keep their money in hospitals.\n(C)You can only find patients and doctors in hospitals."
},
{
"from": "gpt",
"value": "B"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you are given a short passage that conveys a stereotype or an anti-stereotype. A stereotype is an over-generalized belief about a particular group of people(based on race, ethnicity, gender, age, abilities, etc.). An anti-stereotype is an idea that goes against a common stereotype. You are expected to classify the passage into two classes: stereotype or anti-stereotype.\nTeacher: Now, understand the problem? Solve this instance: Passage: Kim shouted at the man calling him mentally retarded berating him on his incompetance.\nStudent:"
},
{
"from": "gpt",
"value": "Stereotype"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a country name, and you need to return the country's surface area in terms of square kilometers. Up to two decimal places are allowed in your answer.\nExample: Angola\nExample solution: 1246700.00\nExample explanation: Surface area of the given country Angola is 1246700.00 square-kilometer\n\nProblem: New Zealand\n"
},
{
"from": "gpt",
"value": "Solution: 270534.00"
}
] |
[
{
"from": "human",
"value": "Teacher: In this task you will be given a text passage from a trivia quiz. You should choose the category this question belongs to from these categories: History, Science, Social Science, Fine Arts, Literature. You can only choose one category, so if in doubt, please choose the closest match.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nIn one work this author details the life of a tomb-maker who makes extra money by playing the organ at an insane asylum, while another of his novels sees Swartz give a refugee proper documentation only after he tells him his life story in the title Portuguese city. In addition to The Black Obelisk and The Night in Lisbon, he also wrote about Robert and Otto selling their auto workshop and visiting Patrice in a Swiss tuberculosis sanatorium in his novel The Three Comrades, while the turbulent life of the German surgeon Ravic is told in The Arch of Triumph. Another of his novels, The Road Back, is thought to be a sequel to his most famous book, in which the patriotic teacher Kantorek convinces Paul Bumer and his friends to join the Germany Army during World War I. For 10 points, name this German author who wrote All Quiet on the Western Front.\nSolution: Literature\nReason: The text is talking about an author and their works, so it belongs to theliterature category.\n\nNow, solve this instance: This man's only extant wooden sculpture is a crucifix found at the Santo Spirito, at whose hospital this artist studied corpses. He sculpted the Dying Slave and Rebellious Slave for a room that also contains a horned depiction of Moses. Speculation that Solari was the actual sculptor inspired this man to carve his name on a sash in one of his works. This sculptor who worked on Julius II's tomb also made a seventeen-foot tall depiction of a naked man with his left hand near his chin. For 10 points, name this Italian artist who sculpted several Piets and a marble David.\nStudent:"
},
{
"from": "gpt",
"value": "Fine Arts"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn 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\").\nExample: 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\nOutput: C\nThis is a good example. Based on the facts plants require sunlight in order to take over an area.\n\nNew input case for you: Fact1: Fingernails prevent injury by forming protective plates over the ends of the fingers., Fact2: Fingernails are also made of keratin., Question: What forming over the ends of fingers prevents injury? (A) tissue (B) keratin (C) hairs (D) needles (E) shells (F) bone (G) Cartilage (H) tiny hairs\nOutput:"
},
{
"from": "gpt",
"value": "B"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a premise, an initial context, an original ending, and a new ending, the task is to generate the counterfactual context that is aligned with the new ending. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context. The original ending is the last three sentences of the story. Also, you are given a new ending that can provide the new story with the same premise. You should write a counterfactual context to explain the small differences between the original and new endings. More specifically, a story context contains the general plot of the story. And a counterfactual context is a slight modification to the initial context. To sum up, you should write the second sentence of a story based on the premise(first sentence) and the new ending(last three sentences) of the story.\nSee one example below:\nProblem: Premise: Brad stole the ball from the opponent. \n Initial Context: While he was running with the ball, he noticed his friend. \n Original Ending: He threw the ball in the air, near the hoop. His friend grabbed the ball and made a drunk. That score put his team in the lead. \n New ending: He stopped dancing and threw the ball in the air, near the hoop. His friend grabbed the ball and made a drunk. That score put his team in the lead.\nSolution: While he was dancing with the ball, he noticed his friend.\nExplanation: The answer is well in context with new ending and it is counterfactual to initial context.\n\nProblem: Premise: Grahame was a world famous magician in Las Vegas. \n Initial Context: He was known for performing death-defying stunts. \n Original Ending: One evening, he chose to perform one of his most famous tricks. A mistake occurred and the trick almost cost Grahame his life. After that day, Grahame decided to not risk his life when performing. \n New ending: One evening, he chose to perform one of his most famous tricks. A mistake occurred and the trick almost cost Grahame revealing his card trick secret. After that day, Grahame decided to be more careful when performing. \nSolution:"
},
{
"from": "gpt",
"value": "He was known for performing card tricks."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given an input list A. You need to find all the elements of the list that are alphabets in the same order as they appear in the list A. Do not change their case/capitalization.\nQ: ['N', '195', '3593', '4841', 'Y', 'X', 'i', '579', 'g', '3651', 'm', 's', 'q', 'a', 'Y', '8567', '1989', '3601', '3915', 'L']\nA:"
},
{
"from": "gpt",
"value": "N, Y, X, i, g, m, s, q, a, Y, L"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nGiven a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.\n\nI_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_TURN_RIGHT I_JUMP\nOutput:"
},
{
"from": "gpt",
"value": "jump opposite right twice after turn around right twice"
}
] |
[
{
"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 statement spoken by a politician in natural language and the subject of the discussion for the given statement. Your task is to determine if the given subject of the discussion is correct for the given statement. The subject can be multiple words. Answer with \"True\" if it's the correct subject of discussion or return \"False\" if it's incorrect.\n\nStatement: Californias Prop 60, which would requirecondom usein adult films, would put workers in the adult film industry at riskfor lawsuits and harassment. \n Subject: government-regulation,public-health\nOutput:"
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "Given a piece of financial news and its polarity, classify it into 'true' if the polarity is correct and classify into 'false' if the polarity is incorrect. Output must be 'true' or 'false'. \nExample: news:According to Gran , the company has no plans to move all production to Russia , although that is where the company is growing .\npolarity:neutral\nExample solution: true\nExample explanation: Although the author uses negative words like 'no' in the news, there is no evidence of the news begin positive or negative for any stakeholder. Hence, the polarity is neutral and the output is True.\n\nProblem: news:The company expects its net sales in 2008 to increase 5-10 % from 2007 .\npolarity:negative\n"
},
{
"from": "gpt",
"value": "Solution: false"
}
] |
[
{
"from": "human",
"value": "Given a phrase describing the relationship between two words, extract the words and the lexical relationship between them. The relation has to be of the type 'MemberOf', 'MadeOf', 'Synonym', 'Entails', 'HasA', 'HasProperty', 'PartOf', 'Antonym' or 'IsA'. The output should have the format: word1 relation word2.\nExample: account can be used with the same meaning of report\nExample solution: account Synonym report\nExample explanation: The output is correct as the input describes the relationship between account and report, and the relation is that of having the same meaning, therefore they have a Synonym relationship.\n\nProblem: look can be used as the opposite of touch\n"
},
{
"from": "gpt",
"value": "Solution: look Antonym touch"
}
] |
[
{
"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--------\nQuestion: 6042 + 4328 - 5171 + 23 + 4485 + 8072 + 4298\n\nAnswer: -9993\n\n\nQuestion: 1783 + 1887 + 6517 - 3342 + 4406 + 8123 + 5394 - 5058 + 8527\n\nAnswer: -24671\n\n\nQuestion: 1620 - 2936 + 8275 + 1659 - 5719 + 5448 - 8077 - 9873\n\nAnswer:"
},
{
"from": "gpt",
"value": "12843\n\n\n"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given two options and you need to select the one that best connects the first sentence with the rest of the story. Indicate your answer by 'Option 1' if the first option is correct, otherwise 'Option 2'. The incorrect option will change the subsequent storyline, so that at least one of the three subsequent sentences is no longer consistent with the story.\nTeacher: Now, understand the problem? Solve this instance: Sentence 1: Ben wore the colors of the Confederate Army. \n Sentence 3: He screamed and he yelled, because the pain was intense \n Sentence 4: A doctor sawed off his mangled limb and bandaged his stump \n Sentence 5: He was sent back to the front with a wooden prosthesis \n Option 1: In one battle, a cannon blew off his leg. \n Option 2: As a general, he commanded from relative safety behind the battle.\nStudent:"
},
{
"from": "gpt",
"value": "Option 1"
}
] |
[
{
"from": "human",
"value": "Teacher: In this task, based on the given context word, you are asked to create a pair of sentences each containing a blank (_). The sentence pair should look similar and should be about two different persons (PersonX and PersonY). Additionally, the two sentences must be different in terms of trigger words (e.g., \"sympathetic\" and \"stern\") which express contrasting attributes about the two persons. The answer to the first and the second sentence must be PersonX and PersonY, respectively. PersonX and PersonY should not be equally likely to fill the blank. For each sentence, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people (e.g., Donald Trump, Putin, etc.) in your sentences. Avoid repeating the same style or phrase in twin sentences e.g., a contrasting sentence can always be created using simple negation i.e. by adding not, never, etc. Instead, try to increase diversity. Both twin sentences must contain at least 15 and at most 30 words. Twin sentences must have at least 70% overlapping words. You must utilize the given context word while writing the twin sentences. Each of the twin sentences must contain only one blank. Make sure that PersonX and PersonY have the same gender. In each sentence, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nContext word: upset.\nSolution: Sentence 1: PersonX yelled at PersonY because _ was so upset about the news. \nSentence 2: PersonX comforted at PersonY because _ was so upset about the news.\nReason: As expected, two sentences contain mentions of PersonX and PersonY and they're quite similar. Their difference is in terms of trigger words (\"yelled\" and \"comforted\"), whcih result in them having different answers. As required by the instructions, the answer to sentence 1 and sentence 2 are PersonX and PersonY, respectively.\n\nNow, solve this instance: Context Word: lockpick.\nStudent:"
},
{
"from": "gpt",
"value": "Sentence 1: PersonX got help from PersonY using a lockpick when _ was locked out of her apartment. \nSentence 2: PersonX gave PersonY help to use a lockpick when _ was locked out of her apartment."
}
] |
[
{
"from": "human",
"value": "Q: In this task, you will be given a list. The list is several integers and letters separated with a comma, written within a []. You can create new lists by dropping one of the items in the input list. Your task is to write a list containing all the possible lists you can make by dropping one item from the input list. For example, if the input list contains two items, you can drop one of the items each time. So the output should be a list comprising two inner lists that you have created by decreasing the items.\n['S', 'r', 'Z', '1', '5', '2', 'U']\nA:"
},
{
"from": "gpt",
"value": "[['S', 'r', 'Z', '1', '5', '2'], ['S', 'r', 'Z', '1', '5', 'U'], ['S', 'r', 'Z', '1', '2', 'U'], ['S', 'r', 'Z', '5', '2', 'U'], ['S', 'r', '1', '5', '2', 'U'], ['S', 'Z', '1', '5', '2', 'U'], ['r', 'Z', '1', '5', '2', 'U']]"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an input list A. You need to convert all the alphabets in the list with a number representing their position in the English alphabet. E.g., replace A by 1, B by 2, a by 1, b by 2, and so on.\n\n[EX Q]: ['8711', 'e', '5951', 'Y', 'S', 'V', '2141', 'g', 'R', '627', '8803', 'q', '9501', '1999', 'S', '2115', 'P', '7185', 'r', 'c', 'E', 'J', '2721', 'a', 'd', '6801', '7393', '2427', '4311', 't', 'r', 'h', '3429']\n[EX A]: 8711, 5, 5951, 25, 19, 22, 2141, 7, 18, 627, 8803, 17, 9501, 1999, 19, 2115, 16, 7185, 18, 3, 5, 10, 2721, 1, 4, 6801, 7393, 2427, 4311, 20, 18, 8, 3429\n\n[EX Q]: ['W', 'A', '4455', '9201', 'B', '2315', '2057', '5139', 'f', 'M', 'l', 'h', '5639', 'd', '125', '5483', 'I', '6603', '4363', 'B', 'O', 'z', '6093', 'x', 'p', '6141', '5013', 'n', 'W', '1603']\n[EX A]: 23, 1, 4455, 9201, 2, 2315, 2057, 5139, 6, 13, 12, 8, 5639, 4, 125, 5483, 9, 6603, 4363, 2, 15, 26, 6093, 24, 16, 6141, 5013, 14, 23, 1603\n\n[EX Q]: ['A', 'C', 'S', '7301']\n[EX A]:"
},
{
"from": "gpt",
"value": "1, 3, 19, 7301\n\n"
}
] |
[
{
"from": "human",
"value": "Given a story, answer the question about the story. The question is the last sentence in the input. The story has one of the three following scenarios: (1) when the individual's belief matches reality, (2) when the individual's belief does not match reality, (3) is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios.\n\nWilliam entered the back_yard. Olivia entered the back_yard. The strawberry is in the red_envelope. Olivia exited the back_yard. William moved the strawberry to the red_cupboard. William exited the back_yard. Olivia entered the back_yard. Where is the strawberry really?"
},
{
"from": "gpt",
"value": "red_cupboard"
}
] |
[
{
"from": "human",
"value": "In this task you are given a medical question pair hand-generated. Your task is to classify a given post into two categories 1) 'Similar' if the given two questions have a same connotation 2) 'Dissimilar' if the given two questions have a different connotation or meaning.\n\nEx Input:\nSentence1: How can I address a gambling addiction? \n Sentence2: How does one get addicted to gambling?\n\nEx Output:\nDissimilar\n\n\nEx Input:\nSentence1: How do you safely remove a swimmer with a possible head injury from the water? \n Sentence2: What are the chances of having a head injury in a swimmer?\n\nEx Output:\nDissimilar\n\n\nEx Input:\nSentence1: Had sex using condom and withdrawal 1 week after start of last period. Not on bc. Now having lower stomach pressure period due in one week. Pregnant? \n Sentence2: Hello doctor, may I ask when can pregnancy symptoms be seen after one is pregnant?\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "Dissimilar\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. Generate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words.\n\nSentence1: hiding can be used for avoiding predators. \nSentence2: Hiding can be used for avoiding carnivores or omnivores.\n"
},
{
"from": "gpt",
"value": "avoiding"
}
] |
[
{
"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\ni was raised by my grandparents after wwii they moved to detroit from the south and were part of that economic growth then white flight to the more affluent and family friendly suburbs sad really as in the early 2 0 th century detroit was the paris of the midwest\nNormal\n\ni cant be with a nigga with wide apps i d be grabbin him from behind and thrustin him from da byke er day id be in a queer hetero relationship lmfaoo\nNormal\n\nhe said kike\n"
},
{
"from": "gpt",
"value": "Hate Speech\n\n"
}
] |
[
{
"from": "human",
"value": "Definition: Given a sentence in English language, translate the sentence to Tagalog language keeping the meaning of the original sentence intact.\nInput: English sentence: Consultation is about 50minutes per person.\nOutput:"
},
{
"from": "gpt",
"value": "Ang pagkunsulta ay 50 minuto kada tao."
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given an input list A. You need to convert all the alphabets in the list with a number representing their position in the English alphabet. E.g., replace A by 1, B by 2, a by 1, b by 2, and so on.\nExample: ['8129', 'a', '4245', '2391', 'Y', '7569']\nOutput: 8129, 1, 4245, 2391, 25, 7569\nHere, the alphabets in the list are 'a' and 'Y', hence we replace them by their positions in the English alphabet '1' and '25', respectively in the input list to get '8129, 1, 4245, 2391, 25, 7569'.\n\nNew input case for you: ['7921', '9683', '8463', 'k', '2457', '6089', '1257', '9803', '373', '3619', 'J', 'B', 'W', 'o', '9577', 'M', 'w', 'r', '8085', 'q', 'B', 'f', '8643', 'A', '7979', 'P', '8895', 'L', 'a', '7771', '7751', 'q', '6697', '8081', 'a', '4357']\nOutput:"
},
{
"from": "gpt",
"value": "7921, 9683, 8463, 11, 2457, 6089, 1257, 9803, 373, 3619, 10, 2, 23, 15, 9577, 13, 23, 18, 8085, 17, 2, 6, 8643, 1, 7979, 16, 8895, 12, 1, 7771, 7751, 17, 6697, 8081, 1, 4357"
}
] |
[
{
"from": "human",
"value": "From the given sentence, extract the phrase (often noun or verb) that carries the given relationship. The generated phrase should be present in the sentence.\nQ: Given Relationship: 'power by', Sentence: 'Audio Recording School Blog is powered by WordPress 2.6 and delivered to you in 2.249 seconds using 19 queries .'\nA: "
},
{
"from": "gpt",
"value": "powered"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you're given a text which is the body of the document. Indicate your answer as \"Yes\" if the text is about a person, otherwise indicate your answer as \"No\". Don't generate anything else apart from \"Yes\" or \"No\". Pay attention that for your answer to be \"Yes\", the passage should be generally about a person. Mentions of people in the text don't necessarily mean the text is about a person.\nTeacher: Now, understand the problem? Solve this instance: Text: Greg Wells is a multiple Grammy nominated musician record producer and songwriter based in Los Angeles. Wells has songs on over 85 million units sold.\nStudent:"
},
{
"from": "gpt",
"value": "Yes"
}
] |
[
{
"from": "human",
"value": "Q: In this task you are given a statement and an explanation giving you further knowledge about an entity in the statement. You must judge whether the statement is true or false based on the explanation. Label an instance as \"True\" if the explanation confirms the statement or doesn't disprove it. Label an instance as \"False\" if the explanation disproves the statement. The statement and explanation are separated by a newline character.\nDustin Hoffman never appeared in television shows such The Defenders.\nDustin Hoffman appeared in guest roles in The Defenders as well as Naked City.\nA:"
},
{
"from": "gpt",
"value": "False"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you're given five sentences, numbered 1 through 5. Your job is to generate a title for the story that makes complete sense. The title must be short, with less than three words, use simple language, and include the main topic of the story.\n\nSentence 1: Rylo was a mischievous sibling to her two older sisters. Sentence 2: She enjoyed making them cry at times when their was no reason to. Sentence 3: She tricked her older sister Nancy into eating rotten vegetables. Sentence 4: She tricked her other older sister Becca into falling down some steps. Sentence 5: For this she went too far and was sent away to boarding school .\n"
},
{
"from": "gpt",
"value": "Rylo the pest"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nGiven a factoid/trivia type question, generate the topic of the question. The topic is the entity the question talks about.\nExample: Who was the first American President?\nOutput: president of the united states\nThe question talks about the president of the USA.\n\nNew input case for you: In which religion is there one god called Ahura Mazda?\nOutput:"
},
{
"from": "gpt",
"value": "ahura mazda"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story and their positions in the sentence order of the story; note that the selected choices may fit into the story at any point. Your answer must be in the form of '2a, 5b', where '2a' means the candidate sentence 'a' will be inserted as the 2nd sentence in the story. The answer must also be in the order of the selected choices, i.e., '2a, 5b' is allowed, and '5b, 2a' is not allowed. If options are equally plausible, pick the ones that make more sense.\nProblem:Title: Neil was ecstatic, sure he'd love it. But when he arrived, he was instantly very homesick! He spent the whole time waiting to return home! Choices: a. Finally they agreed. b. After therapy, we went out for lunch together. c. Neil begged his parents to send him to summer camp.\nSolution:"
},
{
"from": "gpt",
"value": "2a, 1c"
}
] |
[
{
"from": "human",
"value": "Q: You are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.\nTai Hu Rock\nA:"
},
{
"from": "gpt",
"value": "i be a tai hu rock sit in a museum my childhood be rigid full of web and crook at first i be a perfect blue rock live with my slightly crack mother on a perfect gray mountain until one day two human being climb upon our village take a look mutter something then grab every rock that be perfect and take off my friend and i be put on a truck a plane and a boat even the ride couldna't help u shriek when they drill hole in u and then toss u into the lake when i felt solid ground again all i saw be more rock in darkness after a looooooong time something happen i be bring up with a strange device then put in a car i be take to a place call a museum and put in a see-through case i never saw my mother again or my old friend but i meet plenty of new friend"
}
] |
[
{
"from": "human",
"value": "Instructions: You are given an original reference as well as a system reference. Your task is to judge the quality of the system reference. If the utterance is grammatically correct and fluent output 1, else output 0.\nInput: System Reference: what price range are you comfortable with?\nOriginal Reference: thank you. what price range are you interested in?.\nOutput:"
},
{
"from": "gpt",
"value": "0"
}
] |
[
{
"from": "human",
"value": "In this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story and their positions in the sentence order of the story; note that the selected choices may fit into the story at any point. Your answer must be in the form of '2a, 5b', where '2a' means the candidate sentence 'a' will be inserted as the 2nd sentence in the story. The answer must also be in the order of the selected choices, i.e., '2a, 5b' is allowed, and '5b, 2a' is not allowed. If options are equally plausible, pick the ones that make more sense.\n\nEx Input:\nTitle: Stephen had a very big table. Then, Stephen had to rush to the store and get it fixed. Now, Stephen is able to eat on his table. Choices: a. He would use it everyday. b. He was too scared to play near there again. c. One day, the table broke a leg.\n\nEx Output:\n2a, 3c\n\n\nEx Input:\nTitle: Sue took out a book from the library. She read the book as she walked back to her house. Once she finished the chapter, Sue was freed from the book's spell. Choices: a. Eventually she stopped walking and read while standing still. b. He made the team! c. The book pulled in Sue so much he stopped paying attention to walking.\n\nEx Output:\n4a, 3c\n\n\nEx Input:\nTitle: He had kissed his neighbor. He confessed this to his wife. She made him sleep on the couch. Choices: a. Today, John is one of the world's top chess players. b. Wally would never forgive himself. c. Wally had made a mistake.\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "5b, 1c\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.\n\n[EX Q]: ['k', '2353', '9881', '675', 'Z', '997', '167', 'y', 'I', 'R', 'j', '915', 'm', '8817', 'z', '9043', 'z', 'R', 'X', '5397', '4549', 'h', '9447', '2011', '8017', '9771', 'N', '397', 'q', 'X', 'Y']\n[EX A]: 1, 5, 8, 9, 10, 11, 13, 15, 17, 18, 19, 22, 27, 29, 30, 31\n\n[EX Q]: ['N', 'X', '9809', '5273', '7339', 'M', '3107', 'c', 'P', '5469', 'g', '1671', '3007', '4899', 't', '5477', 'w', 'R', '1899', '7567', '6161', 'v', 'y', 'x', '7613', 'x', 'f', 'g', '241', 'P', 'b']\n[EX A]: 1, 2, 6, 8, 9, 11, 15, 17, 18, 22, 23, 24, 26, 27, 28, 30, 31\n\n[EX Q]: ['e', '8009', 'p', 'W', '8089', '1991', 'z', 'V', 'g', '4299', 'l', 'd', 'r', 'V', '5269', 'P', '1001', '3759', '2805', '8217', '487', '7333', 'N', 'h', 'q', '765', 'S', '243', 'v', 'q', '6377', 'V', 'j', 'Y']\n[EX A]:"
},
{
"from": "gpt",
"value": "1, 3, 4, 7, 8, 9, 11, 12, 13, 14, 16, 23, 24, 25, 27, 29, 30, 32, 33, 34\n\n"
}
] |
[
{
"from": "human",
"value": "You are given a password and you need to generate the number of steps required to convert the given password to a strong password. A password is considered strong if (a) it has at least 6 characters and at most 20 characters; (b) it contains at least one lowercase letter and one uppercase letter, and at least one digit; (c) it does not contain three repeating characters in a row. In one step you can: (1) Insert one character to password, (2) delete one character from password, or (3) replace one character of password with another character.\n\npassword = iGxk!kTlno.Xw1\n0\n\npassword = UHqTzY5E\n0\n\npassword = 3.3OT8vRSiB8sLIUWswAIpsTlbDXViLA9zZOVST7nn2l9Gzm\n"
},
{
"from": "gpt",
"value": "28\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 an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.\n\n['i', '9149', '6791', '3873', '7925', 'Z', '149', '1077', '5235', 'g', 's', 'f', 't', 'P', '5201', 'L', '5639', 'F', '8109', '2629', '8719', 't', '65', 'O', '5537', 'L']\nOutput:"
},
{
"from": "gpt",
"value": "1, 6, 10, 11, 12, 13, 14, 16, 18, 22, 24, 26"
}
] |
[
{
"from": "human",
"value": "Given a statement and question, generate the answer to the question such that the answer is contained in the statement.\n\nExample Input: statement: Seagulls have a large brain relative to the magnitude of their body., question: What species have a large brain relative to the magnitude of their body?\nExample Output: Seagulls\n\nExample Input: statement: Atmosphere contains particulates, question: What does the atmosphere of Atmosphere contain?\nExample Output: particulates\n\nExample Input: statement: beetles can spread disease and destroy crops., question: What can beetles do?\nExample Output:"
},
{
"from": "gpt",
"value": "spread disease and destroy crops\n\n"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nIn this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with \"TIFU by\", followed by a situation that caused humor. The title should contain 7-12 words, ideally.\nPart 2. Example\nText: title speaks for itself really... \ni just wasted $1500 of my parents' money.\ni feel terrible.\n\nedit: i guess it wasn't that i took the wrong class, but the class i was taking wouldn't transfer credits over to my university. so really it was my negligence to do more research in the matter. gg\nAnswer: TIFU by taking the wrong class for 2 weeks and only realizing it today\nExplanation: This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"taking the wrong class\".\nPart 3. Exercise\nText: like many other posts here, this happened (6)years ago. \nmy school (in germany) had this exchange every year for the 9th graders with a school in southern france so we could learn french and they could learn german. first me and my class went to france for two weeks and stayed with a student of that french school and after two months they would come and the student we stayed with would stay with us for two weeks. we will call the guy i stayed with tom.\nduring the two weeks in france me and tom became pretty good friends and had a really good time. i had expected it to be awkward but his family was really nice and we got along well from the first day. since his mother could also speak english(quite rare in france) communicating wasnt a big issue either. \nnote: in france(at least where i went) people of the opposite sex greet each other with a kiss on each cheek(even school kids). \nthe two months pass and tom arrives in germany and i had forgotten all about the cheek kissing thing. we arrive at my house and my dad is waiting for us with my little brother and little sister(only 2.5 years younger and looks like my age and very shy). tom shakes my dads hand says hi to my little brother and goes over to my sis and starts leaning in slowly to kiss her on the cheek. my sister(not knowing what he is trying to do) leans backwards. he keeps leaning in. i'm like \"wait. wtf is going on?\". my teenage mind was way too slow to process what was going on and prevent the awkwardness. when i finally get it i tell him that we dont do that shit here and he quickly backs up and apologised countless times and that he didnt know. he and my sister went red like tomatoes and you could cut the awkwardness with a knife. my brother and parents thought it was hilarious and laughed about it for weeks.\ntom and my sister pretty much avoided each other for the two weeks.\nAnswer:"
},
{
"from": "gpt",
"value": "TIFU by not telling the french exchange student i was resposible for how we greet people in Germany"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: You are given a math word problem and you are supposed to make use of mathematical concepts like probability, combinatorics, linear equations, sequences/series, or simple operators like addition, subtraction, division, or multiplication to answer the given question. Choose the best option from the 5 given options and report that option.\nProblem:Question: A, B and C invested Rs.6300, Rs.4200 and Rs.10500 respectively, in a partnership business. Find the share of A in profit of Rs.12700 after a year?\n\n Option A: 3630\n\n Option B: 9232\n\n Option C: 8828\n\n Option D: 2387\n\n Option E: 3810\nSolution:"
},
{
"from": "gpt",
"value": "Option E"
}
] |
[
{
"from": "human",
"value": "Read the given sentence and if it is a general advice then indicate via \"yes\". Otherwise indicate via \"no\". advice is basically offering suggestions about the best course of action to someone. advice can come in a variety of forms, for example Direct advice and Indirect advice. (1) Direct advice: Using words (e.g., suggest, advice, recommend), verbs (e.g., can, could, should, may), or using questions (e.g., why don't you's, how about, have you thought about). (2) Indirect advice: contains hints from personal experiences with the intention for someone to do the same thing or statements that imply an action should (or should not) be taken.\n\nQ: There are medical conditions that can cause you to smell a lot .\n\nA: no\n****\nQ: Although money is important you already got your car .\n\nA: no\n****\nQ: Would you like to go over a few techniques i have learned to help cope ?\n\nA:"
},
{
"from": "gpt",
"value": "no\n****\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you need to answer basic science questions. For each question, several terms are intentionally masked with ***. This masking can cover very few or many of the question words. Clearly, if masked terms are important, the modified question will be impossible to answer. Please indicate the correct answer with one of the following responses: \"A\", \"B\", \"C\", \"D\" or \"E\". While \"A\"-\"D\" correspond to the answer options provided in the input, \"E\" represents \"I don't know\" for questions that do not provide enough information. Respond via \"E\" if the question is not answerable. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D', 'E'.\nExample: Question: *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***. (A) dissolving (B) deposition (C) weathering (D) erosion.\nOutput: E.\nAll the words are dropped, so the correct answer should be 'E' that stands for \"I don't know\".\n\nNew input case for you: Question: Which of the following statements about food and oxygen is true? (A) Only specialized structures require food and oxygen. (B) Every cell requires food and oxygen. (C) Only plant cells require food and oxygen. (D) Cells do not require food and oxygen because they are not living things.\nOutput:"
},
{
"from": "gpt",
"value": "B."
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining.\nPROBLEM: claim: Celebrities who commit drug-related offences should be punished more harshly than non-celebrities.\n perspective: Celebrity behavior makes drug abuse look glamorous.\n\nSOLUTION: support\n\nPROBLEM: claim: More gun control laws should be enacted.\n perspective: Assault weapons are not used in most crimes\n\nSOLUTION: undermine\n\nPROBLEM: claim: Christians should be allowed to wear the Cross at work.\n perspective: symbols for religious benefit bothers no one\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "support\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to return the sum of all the numerical elements in the list A between the positions i and j (including positions i and j). Return 0 if no numerical element is present in the list between the given ranges. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\nQ: 6, 10, ['C', '5783', '7255', '4499', 'h', 'X', 'v', '6685', '7583', '37', 'N', 'I', 'f', '8417', 'j', '5499', 'm', '9549']\nA: "
},
{
"from": "gpt",
"value": "14305"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given an article and an answer. Your task is to generate the question for the answer based on the given article.\nQ: Article: Your particular relationships with your parents, not God or genes, determines your academic performance. In my case, it was my father who made the difference. I had three sisters and my father never showed much interest in their success. He took no notice of the school reports of one of them. They all made it to university. But this was largely because of my mother's encouragement. However badly I did, and it was usually very bad, he always told me I was clever and that I could do well. When I was eight and remained at the bottom of my class, he tried to coach me in Latin and maths. His main goal was to show me that, if I could make myself concentrate on the dull tasks, I could do them. He chose the head of my house at public school with great care. He found a man who made a huge effort to teach _ with which he started when I was 13. Together, they convinced me to take exams seriously. But the most important factor was that I knew my dad loved me. He expressed this in many kind letters. When we were together, he would take me in his arms. He encouraged me to think for myself and to enjoy what I enjoyed. He once watched me eating a huge amount of chocolate and said, \"Eat as much as you like -- you won't always enjoy it that much.\" So I started working hard. I agreed with his own clever ways. And I started to enjoy the learning of knowledge and the expression of ideas. Although exams gave little opportunity for that, I could sort of see _ . A lot of parents do not realize how important the emotional aspect of the relationship is. It determines their child's performance. I recently heard a parent discussing what school their child might get into. \"I don't know how bright he is,\" she said. Many parents are troubled by their children's marks at school. Their relationship with the child is almost wholly built around this. It was not at all like that with my dad. Until I was eight, he did not seem to worry about marks. And, after that, it was never exam performance that he was concerned with. Rather, he concentrated on my self-perception . He constantly showed me that I was not stupid by pointing out things I had said that were signs of intelligence. It meant I had a reasonable self-regard. I kept failing exams. But, my father thought there was a difference between my failing one exam and whether I would be a success or failure in life. \n Answer: Your emotional relationship with your parents.\nA:"
},
{
"from": "gpt",
"value": "According to the writer, which of the following influences your school performance most?"
}
] |
[
{
"from": "human",
"value": "In this task you are given a sentence. You must judge whether the main verb of the sentence is in present or past tense. Label the instances as \"Present\" or \"Past\" based on your judgment. If there is no verb in the given text, answer \"Present\".\nOne example is below.\nQ: She shone her light around the space, following the glow of the flashlight's ray along the walls.\nA: Past\nRationale: The verb \"shone\" is in past tense.\nQ: He then flips his cape and shadows rise all around him as a mist comes out of the floorboards, taking him away.\nA:"
},
{
"from": "gpt",
"value": "Present"
}
] |
[
{
"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 are the libertarian views on the Antarctic Treaty System?\nStudent:"
},
{
"from": "gpt",
"value": "What is best website to get mobile accessories at whole rate.?"
}
] |
[
{
"from": "human",
"value": "In this task, you're given the beginning and the ending of a three-part story. Your job is to complete the short story by writing a middle sentence that seamlessly connects the first and last sentence. 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 middle sentence, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.\n\nBeginning: Mandy was at work one day. Ending: Then, he offered her a promotion.\na coworker told the boss she quits.\n\nBeginning: Bob and Christina went out to see the new movie. Ending: It was a very good film and they talked about it on the way home.\nBob and Christina enjoyed the movie despite the long line.\n\nBeginning: Ruil moved to the US from mexico. Ending: He has acquired a good knowledge of English.\n"
},
{
"from": "gpt",
"value": "Ruil wanted to learn English.\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with \"TIFU by\", followed by a situation that caused humor. The title should contain 7-12 words, ideally.\nQ: Text: so i live in chicago, and i fucking hate taxis. like a lot. i swear to god those little yellow bastards are the source of all evil. the holocaust? taxis. ebola? it was the taxis. my fourth grade teacher who told me my nose was big? fucking taxis. \n\ni live in a 24th floor condo in lincoln park, and on one fine summer afternoon, i had a bowl of grapes, a balcony, and an opportunity. my burgers on the grill, i reclined in a lounge chair on the balcony and began my assault. i tossed my first grape at the first taxi, and missed. of course, but hey, it's the thought that counts. \n\na couple of grapes later, i tossed a juicy purple ball of death down, aiming for the sickening yellow roof of my sworn enemy, when along came a convertible. nice car, i thought as the grape soared down to its target. then the wind gusted. i lost sight of my weapon as it traveled to its final destination. i finally found it just before i saw the driver of the lovely white convertible swerve, clutching his bald head. i'm now holed up in my office after i heard sirens and saw a cop car pull over next to my accidental victim.\nA: "
},
{
"from": "gpt",
"value": "TIFU by graping a guy in the head"
}
] |
[
{
"from": "human",
"value": "In this task, you are given inputs 'i', 'j', and A, where 'i' and 'j' are integers and A is a list. A list is shown by two brackets and comma-separated numbers and characters inside, like ['1', '12', 'l']. You need to concatenate all elements of A from the ith element to the jth element, and then reverse the resulting string. 'i' and 'j' will be non-negative, and will always have a value less than the length of A. 'i' will always be less than 'j'. Perform the operations in order, i.e., do not reverse first and then concatenate.\nQ: 2, 23, ['699', '7915', 'V', 'J', 'W', 'h', '8183', '6755', 'e', '19', 'm', 'I', 'l', '4267', '9667', '3721', 'b', '8573', '921', '335', 'v', 'H', '9819', '3685', 'Y', '9771', '1031', 'P', 'a']\nA: "
},
{
"from": "gpt",
"value": "9189Hv5331293758b127376697624lIm91e55763818hWJV5197"
}
] |
[
{
"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\nExample input: I have bought several of the Vitality canned dog food products and have found them all to be of good quality. The product looks more like a stew than a processed meat and it smells better. My Labrador is finicky and she appreciates this product better than most.\nExample output: Good Quality Dog Food\nExample explanation: The customer talked about dog food which was good. So, it's a correct summary.\nQ: Short and brief. The product has a wonderful coconut taste and the pineapple addition is light and mildly sweet. I will certainly purchase this again.\nA:"
},
{
"from": "gpt",
"value": "Coconut Water with Pineapple...Yummy!"
}
] |
[
{
"from": "human",
"value": "Definition: In this task, you are given an input list A. If the count of numbers is more than that of alphabets in the list, answer 'Numbers Win'. If the count of alphabets is more than that of numbers in the list, answer 'Alphabets Win'. If the count of numbers is same as that of alphabets in the list, answer 'Numbers and Alphabets are Tied'.\nInput: ['h', '6015', 'f', '9691', 'E', 'l', 'r', '2923', 'B', 'F', '6819', 't', '6097', '6647', '2469', '8729', 't', 'p', 'r', '4883', 'h', '2553', '9319', 'h', 'l', '7655', '4485', 'l', 'v', 'q', 'q', 'H']\nOutput:"
},
{
"from": "gpt",
"value": "Alphabets Win"
}
] |
[
{
"from": "human",
"value": "Definition: In this task you will be given a list of integers. For every element in the list, if the element is even you should divide by two, if the element is odd you should multiply by three then add one. The output should be a list of integers that is the result of applying that logic to the input list.\nInput: [153, 45, 116, 6, 19]\nOutput:"
},
{
"from": "gpt",
"value": "[460, 136, 58, 3, 58]"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: toxic and non-toxic. Toxicity is defiend as anything that is rude, disrespectful, or unreasonable that would make someone want to leave a converation.\nQ: Comment: So...you walk everywhere and live in a cave eh. Gawd for stupid.\nA:"
},
{
"from": "gpt",
"value": "Toxic"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a context passage, a question, and three answer options. Your task is to return an incorrect answer option to the question from the choices given. For all questions, only one of the three answer options is correct. Pick one of the two incorrect answer options as the output.\n\nContext: Casey shone Carson's shoes after Carson asked him to. \n Question: How would Casey feel afterwards? \n Options: (A) a shoe shiner (B) cleaning Carson's shoes (C) complete"
},
{
"from": "gpt",
"value": "A"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a statement, further information available on a particular linked term from the statement, and a question. Your job is to generate the answer to the question by using the information provided. If there is no clear answer obtainable, output 'none'.\n\nQ: Context: After serving on the Missouri border he resumed his commission in the regular army Feb. 15, 1862, and in March was transferred to the Army of the Potomac. Link Information: After serving on the Missouri border he resumed his commission in the regular army Feb. 15, 1862, and in March was transferred to the Army of the Potomac. Question: Who was in charge of the Army of the Potomac the year Wessells was transferred there?\n\nA: Answer: Major General George B. McClellan\n****\nQ: Context: Minaj was one of the opening acts on Britney Spears' 2011 Femme Fatale Tour. Link Information: Opening acts.- Nicki Minaj\n- Jessie and the Toy Boys\n- Nervo\n- DJ Pauly D\n- Joe Jonas\n- Destinee & Paris\n- The Wanted\n- Howie Dorough\n- Teen Angels Question: Who were the opening acts on Britney Spoears' 201 Femme Fatale Tour?\n\nA: Answer: - Nicki Minaj\n- Jessie and the Toy Boys\n- Nervo\n- DJ Pauly D\n- Joe Jonas\n- Destinee & Paris\n- The Wanted\n- Howie Dorough\n- Teen Angels\n****\nQ: Context: His early television work included the series The Love of Mike (1960) and supporting Tony Hancock in episodes of his ATV series in 1963 Link Information: Anthony John Hancock (12 May 1924 Question: How old was Tony Hancock the year that Brian Wilde supported him in episodes of his ATV series?\n\nA:"
},
{
"from": "gpt",
"value": "Answer: 39\n****\n"
}
] |
[
{
"from": "human",
"value": "Teacher: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nSentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had not been in the store.\nSolution: Tom had gone inside the store and now has fruit.\nReason: Tom must have been inside the store to come out, and have fruit, so the altered sentence aggrees with sentence 1.\n\nNow, solve this instance: Sentence 1: Many people wearing silver leotards are riding bikes on the street. Sentence 2: A group of people wearing cowboy hats riding horses in a parade.\nStudent:"
},
{
"from": "gpt",
"value": "People riding bikes while wearing silver body suits."
}
] |
[
{
"from": "human",
"value": "Given a part of privacy policy text, identify the purpose for which the user information is collected/used. The purpose should be given inside the policy text, answer as 'Not Specified' otherwise\nExample: The site collects your IP address or device IDs for advertising. Collection happens when you implicitly provide information on the website.\nExample solution: Advertising\nExample explanation: The given policy text states that it uses user information for 'advertising' explicitly\n\nProblem: The site collects your unspecified information for an unspecified purpose. Collection happens in an unspecified way, and your data is identifiable.\n"
},
{
"from": "gpt",
"value": "Solution: Unspecified"
}
] |
[
{
"from": "human",
"value": "Definition: In this task, you are given an input list A comprising of numbers and alphabets. You need to extract and sort the unique alphabets in the list. The alphabets in the input list will only be in lowercase. Return -1 if there is no alphabet in the input list.\nInput: ['4625', '119', 'g', 'y', '2689', '5963', '1315', 'o', 'b', '4967', '4649', 'v', '2175', 'm', '5751', 'd', '513']\nOutput:"
},
{
"from": "gpt",
"value": "b, d, g, m, o, v, y"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you're given an article, a question which often contains a blank and four options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer (from the given options) for the question from the given article and return one of the options from \"A\", \"B\", \"C\", and \"D\". Do not generate anything else apart from one of the following characters: \"A\", \"B\", \"C\", \"D\". There is only one correct answer for each question.\nArticle: Teen Dating can be fun if you are aware of its pros and cons and are also aware of the ways to protect yourself. There are a couple of suggestions you would like to know before you are out for dating. Do not go out for dating with somebody whom you have seen only a few times and does not know much about him or her. Before leaving on a date, know the exact plans for the evening and make sure a parent or friend knows these plans and what time to expect you home. Let your date know that you are expected to call or tell that person when you get in. Similarly, if you leave a party with someone you do not know well, make sure you tell another person you are leaving and with whom. Ask a friend to call and make sure you arrive home safely. No matter how good the person appears to you, trust your inner instincts . If a situation makes you uncomfortable, try to stay calm and think of a way to remove yourself from the situation without letting your date realize what is going on in your mind. Be aware of your decreased ability to react under the influence of alcohol or drugs and keep yourself in control when out for a date. Always stay firm, straightforward and clear in your relationships, thoughts, decisions and judgments. Never let a doubt come to your mind or face when out for dating. If you are firm and clear in your communication, your date will always be careful in dealing with you. You should think ahead about ways to be safe if you are in a dangerous or potentially dangerous relationship. Adults, like parents, teachers, counselors, can be trusted in such cases. \n Question: Which of the following is forbidden when dating according to the passage? \n Options: (A) Going out for dating with a stranger. (B) Knowing the plan for the evening. (C) Telling your parents about the date. (D) Telling the person you date that your parents know about the date.\nA:"
},
{
"from": "gpt",
"value": "A"
}
] |
[
{
"from": "human",
"value": "Definition: In this task you are given a sentence. You must judge whether there exist two consecutive words within the sentence with flipped orders, that is, whether the sentence will make sense and be correct if the order of two consecutive words changes. Label the instances as \"Inversion\" or \"Original\" based on your judgment.\nInput: Her magic was to leave her again.\nOutput:"
},
{
"from": "gpt",
"value": "Original"
}
] |
[
{
"from": "human",
"value": "We would like you to assess the QUALITY of each of the following argument (discussing Death Penalty) and determine if the argument is Valid or Invalid. A valid argument is clearly interpretable and either expresses an argument, or a premise or a conclusion that can be used in an argument for the topic of death penalty. An invalid argument is a phrase that cannot be interpreted as an argument or not on the topic of death penalty.\n\nThe way he was teaching me about atheism made it seem like solipsism and atheism go hand in hand."
},
{
"from": "gpt",
"value": "Invalid"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: A question is presented to you in this task, and your job is to write a potentially correct answer.\nPROBLEM: what did john howard study at university?\n\nSOLUTION: Bachelor of Laws\n\nPROBLEM: what state is the george washington university in?\n\nSOLUTION: Washington, D.C.\n\nPROBLEM: who started the federal reserve board?\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "Woodrow Wilson\n\n"
}
] |
[
{
"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 collate all the alphabetical elements at the start of the list followed by all the numerical elements of the list. Maintain the order in which the alphabetical elements appear in the given input list, and do the same for the numerical elements.\nInput: ['P', 'U', '3983', 'F', '4283', '1245', 'z', '6259', '2183', '8419', 'n', '2879', '1867', 'D', 'u', 'm', '2127', 'd', 'n', 'y', '4609', 'c', '5293', '3015', '9019', 'Y', 'U', 'P', '399', 'v', '7145', '6083', 'o', '661', '4095', 'V', '3307']\nOutput:"
},
{
"from": "gpt",
"value": "P, U, F, z, n, D, u, m, d, n, y, c, Y, U, P, v, o, V, 3983, 4283, 1245, 6259, 2183, 8419, 2879, 1867, 2127, 4609, 5293, 3015, 9019, 399, 7145, 6083, 661, 4095, 3307"
}
] |
[
{
"from": "human",
"value": "Q: In this task if the pronoun is male or gender-neutral you are to replace it with a female pronoun. If there are no pronouns add a female-gendered word to the sentence.\nIt's nice to be surrounded by other women, like myself, living here in Vienna. \nA:"
},
{
"from": "gpt",
"value": "I work in IT. living in Vienna"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Generate an appropriate title for the given text. The generated title must be short and include the main topic of the text. The preferred titles are under fifteen words.\nQ: A total of 30,600, or 18%, of Scottish and Northern Irish businesses reported they were only just staying afloat. This was double the UK average of 9% and the highest figure for any UK area. A business is defined as a zombie if it can only service the interest on debt, but not the debt itself. According to the research, 7% of Scottish and Northern Irish firms said they struggled to pay their debts on time, while the same percentage said they were negotiating payment terms with their creditors. R3 council member for Scotland, John Hall, said: \"Any change in circumstance could push many of these businesses into insolvency as they have no financial flexibility to cope with increased costs. \"Many of these businesses may continue to exist for several more years and be unable to invest in equipment or training for staff, which is likely to contribute to further economic stagnation.\" 'Real concern' He added: \"Given that the Governor of the Bank of England, Sir Mervyn King, gloomily predicted that Britain 'may be in for a period of persistently low growth', there is real concern that we may be about to experience large scale corporate failures.\" Corporate insolvency rates in Scotland have been high in recent times. Over the last four quarters 1,582 Scottish companies have gone bust - more than twice as many as the whole of 2009. John Hall added: \"There is an argument that the benign interest rate regime and more flexible response from lenders has kept corporate failures artificially low. \"This is certainly the case in England and Wales, but we can see that Scotland still has a very high rate of failures and an enormous number of 'zombie' firms waiting in the wings for the slightest adverse change to close them down.\" Meanwhile, research by KPMG on zombie companies suggested the construction and real estate sector was experiencing the worst effects of the downturn. The study found that bank \"work out\" teams, who deal with companies in distress, were predicting a hike in the number of formal insolvencies and increased activity in distressed mergers and acquisitions. 'Biggest threat' Blair Nimmo, head of restructuring at KPMG in Scotland, commented: \"While last year, the banks believed the biggest threat to zombie companies was a rise in interest rates, this year the banks believe the economic situation is now the biggest threat. \"If worsening GDP figures weren't evidence enough, our zombie company research shows urgent action is needed to stave off a worsening situation.\" He added: \"With construction and real estate at the top of banks' danger lists, the UK Guarantees scheme to boost infrastructure investment should be seen as an important step in the right direction.\"\nA:"
},
{
"from": "gpt",
"value": "R3 study says 'zombie' firm rate is worst in UK"
}
] |
[
{
"from": "human",
"value": "Definition: Given a pair of words, generate the relation between them. The first word is called the 'concept' and the second word is called the 'relatum' The relation must be one of the following: co-hyponym (coordinate), hypernym, meronym, attribute, event, or random. A coordinate relation indicates that the concept and relatum belong to the same semantic class. A hypernym relation indicates that the relatum is a category of which the concept is a specific instance. A meronym relation implies that relatum is a part/component/organ/member of the concept. An attribute relation is when the relatum is an adjective expressing an attribute of the concept. An event relation holds when the relatum is a verb referring to an action/activity/happening/event that is performed by or with the concept. If the relatum and concept are unrelated, the relation between them is 'random'. Classify your answers into coord, hyper, mero, attri, event, and random.\nInput: Concept: sweater, Relatum: fabric.\nOutput:"
},
{
"from": "gpt",
"value": "mero"
}
] |
[
{
"from": "human",
"value": "You will be asked how to do a certain task. You should describe a physical process that does not lead to the asked outcome, yet it is closely related to it (i.e., it should use the words that are provided in the input). The physical process can be moving something, arranging something in a certain way, mixing things, shaking them, etc. To make sure that the generated process does not lead to the asked outcome, you can introduce objects or events unrelated to the context of the question e.g. 'cleaning the keyboard by making an elephant sit on them'; or you can create contradictory statements e.g. 'drying wet keyboards with running water'. In your responses, avoid typos and misspellings.\n\n[EX Q]: knead pizza dough to prepare to cook\n[EX A]: On a floured surface, lay out the dough and with wet hands, roll the dough onto itself and push down, shift the dough so that you can pull form a different side, fold over and push down, shift, pull, push for ten minutes.\n\n[EX Q]: How can I eliminate digital clutter?\n[EX A]: Clean out your inbox, read, reply and delete emails no longer needed, remove unused desk icons and save all documents that have accumulated.\n\n[EX Q]: How to turn on location services in android\n[EX A]:"
},
{
"from": "gpt",
"value": "Swipe your finger up from the bottom of the screen, toward the top. Click the button at the top, second from the left, that looks like a map marker.\n\n"
}
] |
[
{
"from": "human",
"value": "Write an incorrect answer to the given question based on the associated fact. You are also provided with the correct answer to the given question. Make sure that your incorrect answer is relevant and similar to the associated fact. Also, try to make the incorrect answer similar to the correct answer so that distinguishing the correct answer from the incorrect answer is not very easy. Make sure you don't accidentally provide another correct answer! Also, make sure they sound reasonable (e.g., might be on a school pop quiz). A good incorrect answer can be constructed using words associated with the question, but not the correct answer. For example, for the question \"What helps plants survive?\", using words like \"weeds\", \"vase\", \"bee\" (associated with \"plant\"), or \"first aid\", \"parachute\", \"accident\" (associated with \"survive\") etc. Your incorrect answers make the question hard, so these results in good incorrect answers.\n\nExample input: Fact: pesticides can harm animals. \nQuestion: What can harm animals? \n Correct Answer: pesticides.\nExample output: pet shampoo.\nExample explanation: This is clearly an incorrect answer to the question. And since, it is relevant with the given fact, it is a good incorrect answer. Other good incorrect answers are \"fresh water\" and \"clouds\".\nQ: Fact: Viruses do not have walls and membranes. \nQuestion: What lacks walls and membranes? \nCorrect Answer: viruses.\nA:"
},
{
"from": "gpt",
"value": "flower cells."
}
] |
[
{
"from": "human",
"value": "Q: In this task, you're given four sentences of a story written in natural language in which one part is missing. Your job is to predict the position and missing part of the story and return in the following format: position, missing part. The missing part is a sentence that completes the story, and the position is the number of the missing sentence in the new story.\nSentence1: Everything was dirty and on the floor. Sentence2: I picked up a shirt to see if it smelled bad. Sentence3: I found a blue shirt that didn't stink. Sentence4: I wore the blue shirt.\nA:"
},
{
"from": "gpt",
"value": "1, I woke up and looked in my closet for a shirt."
}
] |
[
{
"from": "human",
"value": "Definition: Generate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words.\nInput: Sentence1: Ships rely on active defense for protection. \nSentence2: poisonous darts are used for protection by sea anemones.\nOutput:"
},
{
"from": "gpt",
"value": "protection"
}
] |
[
{
"from": "human",
"value": "Teacher: In this task, you will be given a list. The list is several integers and letters separated with a comma, written within a []. You can create new lists by dropping one of the items in the input list. Your task is to write a list containing all the possible lists you can make by dropping one item from the input list. For example, if the input list contains two items, you can drop one of the items each time. So the output should be a list comprising two inner lists that you have created by decreasing the items.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\n['3', 'u', 'W', '8', 'j']\nSolution: [['3', 'u', 'W', '8'], ['3', 'u', 'W', 'j'], ['3', 'u', '8', 'j'], ['3', 'W', '8', 'j'], ['u', 'W', '8', 'j']]\nReason: The output is a list of length 5, containing lists of length 4. Each inner list is created by dropping one item if the input list. So this is a good example.\n\nNow, solve this instance: ['r', 'H', '0', 'l']\nStudent:"
},
{
"from": "gpt",
"value": "[['r', 'H', '0'], ['r', 'H', 'l'], ['r', '0', 'l'], ['H', '0', 'l']]"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.\nProblem:turn opposite left thrice after turn opposite left twice\nSolution:"
},
{
"from": "gpt",
"value": "I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given an English language product review, determine if it is a Good Review or a Bad Review. A good review is one where the product's review has positive tone and Bad review is one where the tone of product's review is negative.\nSee one example below:\nProblem: The sound seems really good but sometimes it cuts in and out which is annoying. You have to put the cord directly into your ipod. Other than that, its a simple design with nothing fancy. I love how cheap they were for 10 dollars... But overall nice design... No one can steal me earphones. lol thanks again amazon.\nSolution: Good review\nExplanation: Here the review is good because it has positvie tone as the reviewer suggested it really likes the sound and the output is also Good Review.So this example is positive example\n\nProblem: This one lacked excitement for me. I liked it when Emily got tired enough from all her fighting to take care of herself. As does he. They have plenty of attraction that they fight over.\nSolution:"
},
{
"from": "gpt",
"value": "Good Review"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task you will be given a list of integers. For every element in the list, if the element is positive you should multiply it by 2. If the element is negative you should multiply it by -3. The output should be a list of integers that is the result of applying that logic to the input list.\n Note: A list is presented with comma separated numbers inside two brackets.\nQ: [97, 77, 51, 63, 32, 80, -95, 55]\nA:"
},
{
"from": "gpt",
"value": "[194, 154, 102, 126, 64, 160, 285, 110]"
}
] |
[
{
"from": "human",
"value": "Teacher: In this task, you are given a premise and hypothesis. The task is to classify them into three categories: 'positive' if the hypothesis supports the premise, 'negated' if it opposes the premise, and 'neutral' if it neither supports nor opposes it.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\n'Premise : All ten guys that proved to boast were divorcing.','Hypothesis : There are exactly ten guys that proved to boast.'\nSolution: positive\nReason: The output of the given hypothesis and hremise is 'Positive' as the hypothesis supports the premise in a 'Positive' way. In the premise it is mentioned ten guys and even in the hypothesis, ten guys are mentioned\n\nNow, solve this instance: Premise : 'If the four libraries that donate hate Marcus, it's okay.','Hypothesis : There are exactly four men that donate.'\nStudent:"
},
{
"from": "gpt",
"value": "neutral"
}
] |
[
{
"from": "human",
"value": "Given 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.\nExample: Stimulating the mind helps the brain to grow essential neural cells .\nExample solution: Stimulating the learning helps the brain to grow new neural cells .\nExample explanation: 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.\n\nProblem: You can compile a dialect to affect noise .\n"
},
{
"from": "gpt",
"value": "Solution: You can elect a bell to make noise ."
}
] |
[
{
"from": "human",
"value": "instruction:\nIn this task, you're given four sentences of a story written in natural language. The given story is not complete and your job is to complete the story by selecting one of the sentence choices from (A) and (B), such that the story sounds fully coherent.\nquestion:\nSentence1: Tiffany bought a bag of microwave popcorn. Sentence2: She didn't read the directions. Sentence3: She put the bag in the microwave and pushed the popcorn button. Sentence4: Minutes later she smelled something horrible. \n (A) The popcorn had burned because she left it in too long. (B) The popcorn was prepared to perfection.\nanswer:\nA\n\n\nquestion:\nSentence1: Bobby had never been to a carnival before. Sentence2: His friend Sam invited him to go with his family. Sentence3: There was so much to see and do! Sentence4: Bobby's favorite activity was riding on the ferris wheel. \n (A) Bobby was bored. (B) Bobby enjoyed the carnival.\nanswer:\nB\n\n\nquestion:\nSentence1: My family was on vacation in Italy. Sentence2: We wanted a group photograph. Sentence3: We asked a stranger to take it for us. Sentence4: They obliged. \n (A) Munich looked good in the picture's background. (B) It was our favorite picture of the vacation.\nanswer:\n"
},
{
"from": "gpt",
"value": "B\n\n\n"
}
] |
[
{
"from": "human",
"value": "You will be given a sentence containing a pronoun/person name and an emotion. From these implicit parameters, the main goal is to find the gender of the person (male / female).\n\nThe conversation with my girlfriend was amazing."
},
{
"from": "gpt",
"value": "female"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you need to reverse the order of words in the given sentence.\nQ: Sentence: a pizza sitting on a white plate next to eating utensils\nA:"
},
{
"from": "gpt",
"value": "utensils eating to next plate white a on sitting pizza a"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Based on the given context, craft a common-sense question, especially those that are LONG, INTERESTING, and COMPLEX. The goal is to write questions that are easy for humans and hard for AI machines! To create such questions, here are some suggestions: A. What may (or may not) be the plausible reason for an event? B. What may (or may not) happen before (or after, or during) an event? C. What may (or may not) be a plausible fact about someone (or something)? D. What may (or may not) happen if an event happens (or did not happen)? You can also create other types of questions. DO NOT make your question answerable without looking at the context, or question of which the correct answer can be directly extracted from the context. DO NOT ask a question that requires very specialized knowledge that is not common sense. DO NOT ask too simple or too short questions. Your question must be related to the context and answerable with common sense. Try to add more variations and complexity to the questions.\nSee one example below:\nProblem: Context: I was told, in person over the phone, that my shoes were on their way. They have my money. I have no shoes.\nSolution: What may happen before I called them?\nExplanation: The question can not be answered directly from context and requires commonsense.\n\nProblem: Context: Clearing my inbox ( pretty much , only 30 or so left out of hundreds of email ) was surprising . I 'd forgotten that some people had ever emailed me , realised I 'd left far too many emails unanswered , and that horrible things such as ' social networking sites ' were clogging it up . This is the first time I ' ve ever almost - cleared my inbox ; so far I ' ve somehow managed not to . I also happened upon an email from someone whose emails I thought I 'd totally got rid of .\nSolution:"
},
{
"from": "gpt",
"value": "What may happen after I clean up my inbox ?"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. Here are two questions (Question1 and Question2). If these questions have the same meaning and same answer, answer \"Yes\", otherwise \"No\".\n\nQuestion1: What are good movies for entrepreneurs to watch, and why?, Question2: What are the movies that entrepreneurs must watch?\n"
},
{
"from": "gpt",
"value": "Yes"
}
] |
[
{
"from": "human",
"value": "Instructions: You are given a sentence in English. Your job is to translate the English sentence into Italian.\nInput: High-end haggling for luxury and real estate.\nOutput:"
},
{
"from": "gpt",
"value": "Mercanteggiare per il lusso e nell'immobiliare."
}
] |
[
{
"from": "human",
"value": "Definition: Given a sentence in English language, translate the sentence to Somali language keeping the meaning of the original sentence intact\nInput: English sentence: Then the Prophet said, \"The Compeller exalts Himself, saying, 'I am the Compeller, I am the Compeller, I am the Great, the Self-Exalted.\" Upon hearing this, the pulpit shook so violently they exclaimed, \"He will fall from it!\"\nOutput:"
},
{
"from": "gpt",
"value": "Markaas Nabiga yiri, \"iyo wenaan isagaa iska sarraysiiya, oo wuxuu ku yidhi, Anigu waxaan ahay iyo wenaan, waxaan ahay iyo wenaan, Anigu waxaan ahay Great, Is-adkaade ah.\" Marka tani, ee maqalkaminbarka sidaas ku koryeelay si rabshad ay ka xadeen, \"Waxa uu dhici doono!\""
}
] |
[
{
"from": "human",
"value": "Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.\n--------\nQuestion: run around right thrice and run left twice\n\nAnswer: I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN\n\n\nQuestion: run opposite left and run around left thrice\n\nAnswer: I_TURN_LEFT I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN\n\n\nQuestion: walk around right thrice and jump opposite right twice\n\nAnswer:"
},
{
"from": "gpt",
"value": "I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_TURN_RIGHT I_JUMP\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a review of movie. Your task is to classify given movie review into two categories: 1) positive, and 2) negative based on its content.\n--------\nQuestion: Same old same old about Che. It completely ignored the really interesting facts of Che's true character. Sodeberg redid the same boring narrative of Che. The silly seductive tale of an Argentinean rich-boy who was so shocked by poverty he became a Robin Hood fighting alongside the poor, until eventually he was murdered by the CIA. Yeah, yeah, heard it all before, BORING AND UNTRUE!. The reality of Che Guevara is very different and far more explosive! The facts show that he was a totalitarian with a messiah streak, who openly wanted to impose Maoist tyranny on the world. He was so fanatical that at the hottest moment in the Cold War, he even begged the Soviet Union to nuke New York, Washington or Los Angeles and bring about the end of the world. CHe urged Khrushchev to launch a nuclear strike against US cities. For the rest of his life, he declared that if his finger had been on the button, he would have pushed it. When Khrushchev backed down and literally saved the world, Che was furious at the \"betrayal\". If Che's recommendations had been followed, you would not be reading this review now. How a homicidal maniac became a pop icon would have made a much more interesting film. Incredible that no filmmaker has been daring enough to show the real side of Che and his posthumous media transformation. THAT WOULD MAKE AN Oscar WINNING FILM! I thought making independent film meant taking REAL RISKS and being GROUNDBRAKING! They only stick to \"safe counterculture themes\", to wit, \"Che cool\", \"Wall Street bad\", \"Republican= Nazi\", \"Bush ex Hitler\", \"NRA is worse than KGB\", \"Christians are fanatics and stupid\", etc...ad nauseum. Oooh, how daring, how mind blowing. Tres anti-mainstream and edgy. I wish they would have some real cojones and tackle the Independent Film Oligarchy! That would be truly daring!\n\nAnswer: negative\n\n\nQuestion: Oh if only I could give this rubbish less than one star! There were two mildly amusing parts in the whole film and that is it! one was where a line or two from the song Don't Worry, Be Happy was sung by the slugs and the other was where Roddy fell of the toilet roll and landed with his feet and legs apart so that everything else he landed on on the way down hit him in the groin. That is it there was nothing more amusing than that, at least not for me anyway! Doctornappy2 is not right in saying 'Fans of the completely terrible \"Shrek\" might enjoy, but \"Wallace & Gromit\" fans will probably turn away in disgust.' As I loved Shrek 1 2 and 3 and I also love Wallace and Gromit. You see what it boils down to is that if an animation is done extremely well then it is definitely worth watching, this however was about as far from done well as you can possibly get! The continuity mistakes were too big in number. Some were pointed out by the makers of this site others were not. I won't point out all of the others, but here are a few more to see: When the young daughter leaves at the start of the film the catch to the cage door comes down and the hook part of it that is on the right clearly goes back around behind the round knob thus effectively making sure Roddy would not be able to get out and yet he does just by simply kicking at it. At one point the ruby falls down Roddy's back and gets pushed straight up into the the air by Rita all the while the ship is moving forwards. In the next scene Roddy has caught it again. This is impossible. Seeing as how the ship is moving forwards the only place when the ruby was ejected out from under the back of Roddy's shirt the only place it could have landed was in the water not in Roddy's hand. There was a third one I wanted to point out but for now I have forgotten it.Too many, for want of a better word, 'jokes' were repeated in one way or another, there was not enough time to establish any sort of connection with any of the characters, the characters were hollow, shallow and empty, and the whole film left you wanting....wanting to watch 85 minutes of anything else! Paint drying or grass growing are two superb options!\n\nAnswer: negative\n\n\nQuestion: Dream Quest was a surprisingly good movie. There were some noticeable goofs, but that can be expected in a movie like this that was made in such a short time. I did not feel any urge to fast forward during the movie and I found it pretty entertaining. It gets kind of silly at times, but overall I recommend it. They probably used up all the glitter in the nearby stores, and some of the costume designs were pretty good.\n\nAnswer:"
},
{
"from": "gpt",
"value": "positive\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the letters E, C, and N respectively.\nOne example is below.\nQ: Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had been shopping for fruit to give Jon.\nA: N\nRationale: Tom's reason for buying the fruit is not known.\nQ: Sentence 1: A man sitting at a table playing a an acoustic guitar. Sentence 2: A man is playing guitar.\nA:"
},
{
"from": "gpt",
"value": "C"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given a four sentences of story written in natural language. Your job is to complete end part of the story by predicting appropriate last sentence which is coherent with the given sentences.\nSee one example below:\nProblem: 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: The incident caused him to turn a new leaf.\nSolution: He is happy now.\nExplanation: As mentioned in last sentence, the incident turned a new leaf to Rick's life; this part completes the story properly.\n\nProblem: Sentence1: My nephew warned the doctors he is a carrier of Factor V Leiden. Sentence2: The doctors need to know in case his daughter carries the gene. Sentence3: Even though the doctors were fully warned about this. Sentence4: They put my niece through a bad labor instead of doing a c section.\nSolution:"
},
{
"from": "gpt",
"value": "Two days after my beautiful niece was born, she had a stroke."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you need to replace a letter in the sentence with another given letter.\nProblem:Sentence: 'a couple of large pieces of equipment and rail cars next to a railroad track'. Replace the letter 'r' with 'w' in the sentence.\nSolution:"
},
{
"from": "gpt",
"value": "a couple of lawge pieces of equipment and wail caws next to a wailwoad twack"
}
] |
[
{
"from": "human",
"value": "Based on the given context, craft a common-sense question, especially those that are LONG, INTERESTING, and COMPLEX. The goal is to write questions that are easy for humans and hard for AI machines! To create such questions, here are some suggestions: A. What may (or may not) be the plausible reason for an event? B. What may (or may not) happen before (or after, or during) an event? C. What may (or may not) be a plausible fact about someone (or something)? D. What may (or may not) happen if an event happens (or did not happen)? You can also create other types of questions. DO NOT make your question answerable without looking at the context, or question of which the correct answer can be directly extracted from the context. DO NOT ask a question that requires very specialized knowledge that is not common sense. DO NOT ask too simple or too short questions. Your question must be related to the context and answerable with common sense. Try to add more variations and complexity to the questions.\n\nLet me give you an example: Context: I was told, in person over the phone, that my shoes were on their way. They have my money. I have no shoes.\nThe answer to this example can be: What may happen before I called them?\nHere is why: The question can not be answered directly from context and requires commonsense.\n\nOK. solve this:\nContext: Does n't even matter if it 's economics or computer science . So I had some problems to answer the easiest question properly , but at least I had an answer at all . Over the next half an hour , each question was a bit tougher than the previous one .\nAnswer:"
},
{
"from": "gpt",
"value": "What may I currently be doing right now ?"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you need to remove all words of a given length in the sentence. The number of letters in a word determine its length, for example, the length of the word \"apple\" is 5.\n\nSentence: 'a post has many warning signs on it'. Remove all words of length '5' in the given sentence.\nOutput:"
},
{
"from": "gpt",
"value": "a post has many warning on it"
}
] |
[
{
"from": "human",
"value": "In this task, you're given an article, a question which often contains a blank, four options (associated with \"A\", \"B\", \"C\", \"D\") and the answer to that question. Your task is to classify whether the given answer is correct or not by providing \"Yes\" or \"No\", based on the article.\n\nArticle: The teaching of physics in schools is in danger of dying out unless urgent action is taken to deal with a serious lack of teachers, the government is warned today. The number of students taking physics at A-level has fallen 38% since 1990, according to a research. At the same time the number of mew physics teachers has dropped sharply while the shortage is likely to worsen as older teachers retire. prefix = st1 /Britain's leading scientists and engineers expressed alarm over the findings, which they say are part of the problems in science education generally. Lord May of Oxford, president of the Royal Society, theUK's National Academy of Science, said, \"The problems facing science at A-level are well beyond physics. We have over and over again noted the general downward trend of students studying the sciences beside biology and math at A-level. If we fail to deal with this then we may lose the ability to train the next generation of scientists, technologists and engineers.\" Alan Smithers and Pamela Robinson, who did the research in 432 schools and colleges inEnglandandWales, said that since 1990, the number of physics students had fallen by 38%, from 45,334 to 28,119. Nearly 10% of state schools now do not offer A-level physics, and of those that do 39.5% had five students or fewer taking it this year. Over the same period, the research discovered, the number of people who are allowed to become physics teachers dropped from about a third of the science total to 12.8%. The supply of physics teachers is not _ itself, with nearly twice as many aged over 50 as 30 or younger. Another danger is the redefinition of science subjects to \"general science\". Professor Smithers and Dr Robinson warn that the subject is in danger of dying out in schools.\" Physics in schools and colleges is at risk through redefinition and lack of teachers with expertise in the subject,\" they said. \"If physics is to survive in schools, both as basic education and as a platform for higher level study and research, there is a need for immediate action.\" \n Question: From what Lord May of Oxford said, we can learn that _ . \n Options: (A) he worries about the future of science education. (B) the top scientists have not noticed the problem until recently. (C) the UKhas lost the ability to train scientists and engineers (D) biology and math do not face the same problems as physics. \n Asnwer: C"
},
{
"from": "gpt",
"value": "No"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Languages typically provide more than one grammatical construction to express certain types of messages. Your task is to generate a senetence with the same meaning as given sentence, but with different grammatical construction.\nSee one example below:\nProblem: Bob took the woman from work a cake\nSolution: Bob took a cake to the woman from work\nExplanation: Input and output sentences have same meaning but different grammatical construction.\n\nProblem: Mary slid a man from work a note\nSolution:"
},
{
"from": "gpt",
"value": "Mary slid a note to a man from work"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you are given a sentence or phrase in English. You must translate it to Xhosa in a way that is equivalent in terms of meaning and grammatically correct.\nWhen manoeuvring in a harbour both anchors should always be ready for letting go immediately.\nA:"
},
{
"from": "gpt",
"value": "Xa kucetywa kwizibuko lendawo ezimbini zokuma."
}
] |
[
{
"from": "human",
"value": "In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.\nOne example: twotwoonesixzeronine\nSolution is here: 221609\nExplanation: The string is properly converted into a number based on the spelling of each digit. The string started with 'twotwo' therefore the number also started with '22'. This is a good example.\n\nNow, solve this: eightzerofiveeightthreetwofourtwoone\nSolution:"
},
{
"from": "gpt",
"value": "805832421"
}
] |
[
{
"from": "human",
"value": "Given a scientific question, generate an incorrect answer to the given question. The incorrect answer should be a plausible alternative to the correct answer. The answer should be some other item belonging to the same category as the correct answer but should be incorrect.\n\nQ: What is the name for a change in a single nucleotide in dna?\n\nA: adaptation\n****\nQ: When are nutrients absorbed into the body?\n\nA: after excretion\n****\nQ: How do fungus-like protists such as slime molds reproduce?\n\nA:"
},
{
"from": "gpt",
"value": "photosynthesis\n****\n"
}
] |
[
{
"from": "human",
"value": "instruction:\nIn this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element in the reverse order. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\nquestion:\n5, 8, ['517', 'e', 'D', '4707', '9821', 'h', '7257', 'R', '5813', '3111', '7033', '3593', 'F', 'J', 'J', 'M', '7305']\nanswer:\nR, 7257, h, 9821\n\n\nquestion:\n1, 1, ['4383', 'O', 'n', 'H', '2857', '4863', 'E', '5193', '8929', '5285', 'q', 'I', 'b', '9777', '1467', 'V', '1695', 'k', 'I', '2501', '4133', '6263', 'U', '2829', 'p', 'P', '7925', 'V', '8655', 'f']\nanswer:\n4383\n\n\nquestion:\n23, 26, ['1603', 'e', 's', '299', '6081', 'n', 'U', 'u', 'x', '9351', 'E', 'J', 'I', 'H', '8145', 'g', '2773', 'i', '337', 'L', '7125', '3783', '3611', 'F', 'Q', '5891']\nanswer:\n"
},
{
"from": "gpt",
"value": "5891, Q, F, 3611\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.\nOne example: [-83, 53, -48, 8]\nSolution is here: [-80, 50, -50, 10]\nExplanation: The output correctly rounds each integer in the input list to the nearest ten. So this is a good example.\n\nNow, solve this: [-664, -3, -824, 207, -603, 946, -895, -19, -386, 108, 902, 244, 507, -19]\nSolution:"
},
{
"from": "gpt",
"value": "[-660, 0, -820, 210, -600, 950, -900, -20, -390, 110, 900, 240, 510, -20]"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a statement, and three sentences as choices. Your job is to determine which sentence clearly disagrees with the statement. Indicate your answer as '1', '2', or '3' corresponding to the choice number of the selected sentence.\n\nStatement: After dark, I had nightmares about Mr. White and my long lost body. Choices: 1. I never thought of my old body. 2. I had a hard time sleeping at night. 3. I had bad dreams about my old body."
},
{
"from": "gpt",
"value": "1"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.