triple1 listlengths 3 3 | triple2 listlengths 3 3 | triple3 listlengths 3 3 | triple1_labels listlengths 3 3 | triple2_labels listlengths 3 3 | triple3_labels listlengths 3 3 | description stringlengths 10 16 | keep_triple bool 1
class | query_prompt stringlengths 3.25k 3.36k | query stringlengths 100 173 | entity_a stringlengths 4 21 | entity_b stringlengths 6 40 | rel_b stringlengths 6 36 | prompt stringlengths 3.57k 3.66k | index int64 300 319 | raw_responses stringlengths 93 4.22k |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
[
"Q2608288",
"P2175",
"Q41112"
] | [
"Q410412",
"P2175",
"Q41112"
] | [
"Q410412",
"P769",
"Q419652"
] | [
"(Z)-thiothixene",
"medical condition treated",
"schizophrenia"
] | [
"carbamazepin",
"medical condition treated",
"schizophrenia"
] | [
"carbamazepin",
"significant drug interaction",
"danazol"
] | Q41112__P2175 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting (Z)-thiothixene, a chemical compound, and a substance that has a significant drug interaction with danazol? | (Z)-thiothixene | danazol | significant drug interaction | Query: What are different ways of connecting (Z)-thiothixene, a chemical compound, and a substance that has a significant drug interaction with danazol?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship, t... | 300 | {"final_response": "<answer>\n{\n \"1\": [\n [\"(Z)-thiothixene\", \"interacts with\", \"carbamazepine\"],\n [\"carbamazepine\", \"significant drug interaction\", \"danazol\"]\n ],\n \"2\": [\n [\"(Z)-thiothixene\", \"treats\", \"Schizophrenia\"],\n [\"Schizophrenia\", \"treated by\", \"quetiapine\"],\n ... |
[
"Q93690192",
"P54",
"Q337758"
] | [
"Q3675476",
"P54",
"Q337758"
] | [
"Q3675476",
"P463",
"Q2839513"
] | [
"Fritz Greenlee",
"member of sports team",
"San Francisco 49ers"
] | [
"Chris Doleman",
"member of sports team",
"San Francisco 49ers"
] | [
"Chris Doleman",
"member of",
"Alpha Phi Alpha"
] | Q337758__P54 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting Fritz Greenlee and someone who is a member of Alpha Phi Alpha? | Fritz Greenlee | Alpha Phi Alpha | member of | Query: What are different ways of connecting Fritz Greenlee and someone who is a member of Alpha Phi Alpha?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship, tail) forming a continuous chain that begins w... | 301 | {"final_response": "```json\n{\n \"1\": [\n [\n \"Fritz Greenlee\",\n \"played for\",\n \"San Francisco 49ers\"\n ],\n [\n \"Charles Haley\",\n \"played for\",\n \"San Francisco 49ers\"\n ],\n [\n \"Charles Haley\",\n \"member of\",\n \"Alpha Phi Alpha\"\n ... |
[
"Q17816452",
"P2293",
"Q128581"
] | [
"Q18047337",
"P2293",
"Q128581"
] | [
"Q18047337",
"P5572",
"Q66004840"
] | [
"AKT1",
"genetic association",
"breast cancer"
] | [
"LRMDA",
"genetic association",
"breast cancer"
] | [
"LRMDA",
"expressed in",
"bone marrow cells"
] | Q128581__P2293 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting AKT1, a gene involved in various cellular processes, and a substance that is expressed in bone marrow cells? | AKT1 | bone marrow cells | expressed in | Query: What are different ways of connecting AKT1, a gene involved in various cellular processes, and a substance that is expressed in bone marrow cells?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship, ... | 302 | {"final_response": "<answer>\n{\n \"1\": [\n [\"AKT1\", \"interacts with\", \"PIK3CA\"],\n [\"PIK3CA\", \"interacts with\", \"KIT\"],\n [\"KIT\", \"expressed in\", \"bone marrow cells\"]\n ],\n \"2\": [\n [\"AKT1\", \"interacts with\", \"MTOR\"],\n [\"MTOR\", \"interacts with\", \"FLT3\"],\n [\"FLT... |
[
"Q171034",
"P166",
"Q38104"
] | [
"Q57072",
"P166",
"Q38104"
] | [
"Q57072",
"P6104",
"Q8487137"
] | [
"Robert Wilson",
"award received",
"Nobel Prize in Physics"
] | [
"Otto Stern",
"award received",
"Nobel Prize in Physics"
] | [
"Otto Stern",
"maintained by WikiProject",
"WikiProject Mathematics"
] | Q38104__P166 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting Robert Wilson, a notable figure in his field, and someone who is associated with the WikiProject Mathematics? | Robert Wilson | WikiProject Mathematics | maintained by WikiProject | Query: What are different ways of connecting Robert Wilson, a notable figure in his field, and someone who is associated with the WikiProject Mathematics?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship,... | 303 | {"final_response": "<answer>\n{\n \"1\": [\n [\n \"Robert Wilson\",\n \"co-authored\",\n \"ATLAS of Finite Groups\"\n ],\n [\n \"ATLAS of Finite Groups\",\n \"maintained by WikiProject\",\n \"WikiProject Mathematics\"\n ]\n ],\n \"2\": [\n [\n \"Robert Wilson\",\n ... |
[
"Q412690",
"P2175",
"Q11081"
] | [
"Q412443",
"P2175",
"Q11081"
] | [
"Q412443",
"P769",
"Q144085"
] | [
"galantamine",
"medical condition treated",
"Alzheimer's disease"
] | [
"risperidone",
"medical condition treated",
"Alzheimer's disease"
] | [
"risperidone",
"significant drug interaction",
"pimozide"
] | Q11081__P2175 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting galantamine, a medication used for treating Alzheimer's disease, and a substance that has a significant drug interaction with pimozide? | galantamine | pimozide | significant drug interaction | Query: What are different ways of connecting galantamine, a medication used for treating Alzheimer's disease, and a substance that has a significant drug interaction with pimozide?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual tr... | 304 | {"final_response": "<answer>\n{\n \"1\": [\n [\"galantamine\", \"interacts with\", \"paroxetine\"],\n [\"paroxetine\", \"significant drug interaction\", \"pimozide\"]\n ],\n \"2\": [\n [\"galantamine\", \"interacts with\", \"ketoconazole\"],\n [\"ketoconazole\", \"significant drug interaction\", \"pimozi... |
[
"Q1033108",
"P162",
"Q3482118"
] | [
"Q1033108",
"P162",
"Q298761"
] | [
"Q298761",
"P106",
"Q18844224"
] | [
"Candyman",
"producer",
"Sigurjón Sighvatsson"
] | [
"Candyman",
"producer",
"Clive Barker"
] | [
"Clive Barker",
"occupation",
"science fiction writer"
] | Q1033108__P162 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting Sigurjón Sighvatsson, a notable figure in the film industry, and someone who is known for their work as a science fiction writer? | Sigurjón Sighvatsson | science fiction writer | occupation | Query: What are different ways of connecting Sigurjón Sighvatsson, a notable figure in the film industry, and someone who is known for their work as a science fiction writer?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples ... | 305 | {"final_response": "<answer>\n{\n \"1\": [\n [\"Sigurj\u00f3n Sighvatsson\", \"produced\", \"Z for Zachariah (film)\"],\n [\"Z for Zachariah (film)\", \"based on\", \"Z for Zachariah (novel)\"],\n [\"Z for Zachariah (novel)\", \"authored by\", \"Robert C. O'Brien\"],\n [\"Robert C. O'Brien\", \"occupation\... |
[
"Q18053449",
"P2293",
"Q11081"
] | [
"Q18032340",
"P2293",
"Q11081"
] | [
"Q18032340",
"P5572",
"Q18717"
] | [
"ZNF438",
"genetic association",
"Alzheimer's disease"
] | [
"VSNL1",
"genetic association",
"Alzheimer's disease"
] | [
"VSNL1",
"expressed in",
"orbitofrontal cortex"
] | Q11081__P2293 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting ZNF438, a gene, and a substance that is expressed in the orbitofrontal cortex? | ZNF438 | orbitofrontal cortex | expressed in | Query: What are different ways of connecting ZNF438, a gene, and a substance that is expressed in the orbitofrontal cortex?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship, tail) forming a continuous cha... | 306 | {"final_response": "<answer>\n{\n \"1\": [\n [\"ZNF438\", \"located on\", \"Chromosome 10\"],\n [\"Chromosome 10\", \"contains\", \"ADRA2A\"],\n [\"ADRA2A\", \"expressed in\", \"orbitofrontal cortex\"]\n ],\n \"2\": [\n [\"ZNF438\", \"part of\", \"Homo sapiens\"],\n [\"Homo sapiens\", \"produces\", \"... |
[
"Q184592",
"P166",
"Q38104"
] | [
"Q153194",
"P166",
"Q38104"
] | [
"Q153194",
"P185",
"Q6104536"
] | [
"Gerard 't Hooft",
"award received",
"Nobel Prize in Physics"
] | [
"Edward Victor Appleton",
"award received",
"Nobel Prize in Physics"
] | [
"Edward Victor Appleton",
"doctoral student",
"J. A. Ratcliffe"
] | Q38104__P166 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting Gerard 't Hooft, the Dutch theoretical physicist, and someone who has been a doctoral student of Edward Victor Appleton? | Gerard 't Hooft | J. A. Ratcliffe | doctoral student | Query: What are different ways of connecting Gerard 't Hooft, the Dutch theoretical physicist, and someone who has been a doctoral student of Edward Victor Appleton?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, re... | 307 | {"final_response": "<answer>\n{\n \"1\": [\n (\"Gerard 't Hooft\", \"award received\", \"Nobel Prize in Physics\"),\n (\"Nobel Prize in Physics\", \"awarded to\", \"Edward Victor Appleton\"),\n (\"Edward Victor Appleton\", \"doctoral student\", \"J. A. Ratcliffe\")\n ],\n \"2\": [\n (\"Gerard 't Hooft\",... |
[
"Q242484",
"P166",
"Q17144"
] | [
"Q1781375",
"P166",
"Q17144"
] | [
"Q1781375",
"P102",
"Q29552"
] | [
"Lynn Fontanne",
"award received",
"Presidential Medal of Freedom"
] | [
"Leo Cherne",
"award received",
"Presidential Medal of Freedom"
] | [
"Leo Cherne",
"member of political party",
"Democratic Party"
] | Q17144__P166 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting Lynn Fontanne, the renowned actress, and someone who is a member of the Democratic Party? | Lynn Fontanne | Democratic Party | member of political party | Query: What are different ways of connecting Lynn Fontanne, the renowned actress, and someone who is a member of the Democratic Party?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship, tail) forming a con... | 308 | {"final_response": "<answer>\n{\n \"1\": [\n [\"Lynn Fontanne\", \"awarded\", \"Presidential Medal of Freedom\"],\n [\"Presidential Medal of Freedom\", \"awarded by\", \"Lyndon B. Johnson\"],\n [\"Lyndon B. Johnson\", \"member of political party\", \"Democratic Party\"]\n ],\n \"2\": [\n [\"Lynn Fontanne... |
[
"Q1230832",
"P40",
"Q1429"
] | [
"Q1427",
"P40",
"Q1429"
] | [
"Q1427",
"P39",
"Q357829"
] | [
"Titus Aurelius Fulvus",
"child",
"Antoninus Pius"
] | [
"Hadrian",
"child",
"Antoninus Pius"
] | [
"Hadrian",
"position held",
"eponymous archon"
] | Q1429__P40 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting Titus Aurelius Fulvus, a notable figure in ancient Rome, and someone who held the position of eponymous archon? | Titus Aurelius Fulvus | eponymous archon | position held | Query: What are different ways of connecting Titus Aurelius Fulvus, a notable figure in ancient Rome, and someone who held the position of eponymous archon?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationshi... | 309 | {"final_response": "<answer>\n{\n \"1\": [\n [\"Titus Aurelius Fulvus\", \"child\", \"Antoninus Pius\"],\n [\"Antoninus Pius\", \"adopted by\", \"Hadrian\"],\n [\"Hadrian\", \"position held\", \"eponymous archon\"]\n ],\n \"2\": [\n [\"Titus Aurelius Fulvus\", \"child\", \"Antoninus Pius\"],\n [\"Anto... |
[
"Q908525",
"P54",
"Q188984"
] | [
"Q3035835",
"P54",
"Q188984"
] | [
"Q3035835",
"P413",
"Q2583758"
] | [
"Don Blackburn",
"member of sports team",
"New York Rangers"
] | [
"Don Marshall",
"member of sports team",
"New York Rangers"
] | [
"Don Marshall",
"position played on team / speciality",
"centre"
] | Q188984__P54 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting Don Blackburn, a notable figure in sports, and someone who played as a center on their team? | Don Blackburn | centre | position played on team / speciality | Query: What are different ways of connecting Don Blackburn, a notable figure in sports, and someone who played as a center on their team?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship, tail) forming a ... | 310 | {"final_response": "<answer>\n{\n \"1\": [\n [\"Don Blackburn\", \"played for\", \"Philadelphia Flyers\"],\n [\"Philadelphia Flyers\", \"has player\", \"Bobby Clarke\"],\n [\"Bobby Clarke\", \"position played on team / speciality\", \"centre\"]\n ],\n \"2\": [\n [\"Don Blackburn\", \"played for\", \"Bost... |
[
"Q421552",
"P2175",
"Q12199"
] | [
"Q425490",
"P2175",
"Q12199"
] | [
"Q425490",
"P769",
"Q3935297"
] | [
"raltegravir",
"medical condition treated",
"HIV/AIDS"
] | [
"indinavir",
"medical condition treated",
"HIV/AIDS"
] | [
"indinavir",
"significant drug interaction",
"rifapentine"
] | Q12199__P2175 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting raltegravir, an antiretroviral medication, and a substance that has a significant drug interaction with rifapentine? | raltegravir | rifapentine | significant drug interaction | Query: What are different ways of connecting raltegravir, an antiretroviral medication, and a substance that has a significant drug interaction with rifapentine?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relati... | 311 | {"final_response": "<answer>\n{\n \"1\": [\n [\"raltegravir\", \"significant drug interaction\", \"rifapentine\"]\n ],\n \"2\": [\n [\"raltegravir\", \"same drug class\", \"dolutegravir\"],\n [\"dolutegravir\", \"significant drug interaction\", \"rifapentine\"]\n ],\n \"3\": [\n [\"raltegravir\", \"tre... |
[
"Q96242252",
"P40",
"Q2667"
] | [
"Q96242216",
"P40",
"Q2667"
] | [
"Q96242216",
"P25",
"Q96242247"
] | [
"Luise Schwickart",
"child",
"Paul von Hindenburg"
] | [
"Hans Robert Ludwig von Beneckendorff und von Hindenburg",
"child",
"Paul von Hindenburg"
] | [
"Hans Robert Ludwig von Beneckendorff und von Hindenburg",
"mother",
"Eleonore von Brederlow"
] | Q2667__P40 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting Luise Schwickart and someone who is the mother of Eleonore von Brederlow? | Luise Schwickart | Eleonore von Brederlow | mother | Query: What are different ways of connecting Luise Schwickart and someone who is the mother of Eleonore von Brederlow?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship, tail) forming a continuous chain th... | 312 | {"final_response": "<answer>\n{\n \"1\": [\n [\n \"Luise Schwickart\",\n \"mother\",\n \"Eleonore von Brederlow\"\n ]\n ]\n}\n</answer>", "response_tokens": 51, "reasoning_tokens": 901} |
[
"Q104855964",
"P162",
"Q93838349"
] | [
"Q104855964",
"P162",
"Q93532910"
] | [
"Q93532910",
"P106",
"Q1414443"
] | [
"A Wife Among Wives",
"producer",
"Judith MacDougall"
] | [
"A Wife Among Wives",
"producer",
"David MacDougall"
] | [
"David MacDougall",
"occupation",
"filmmaker"
] | Q104855964__P162 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting Judith MacDougall, a filmmaker, and someone who is known for their work in the film industry? | Judith MacDougall | filmmaker | occupation | Query: What are different ways of connecting Judith MacDougall, a filmmaker, and someone who is known for their work in the film industry?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship, tail) forming a... | 313 | {"final_response": "<answer>\n{\n \"1\": [\n [\"Judith MacDougall\", \"occupation\", \"filmmaker\"]\n ],\n \"2\": [\n [\"Judith MacDougall\", \"spouse\", \"David MacDougall\"],\n [\"David MacDougall\", \"occupation\", \"filmmaker\"]\n ],\n \"3\": [\n [\"Judith MacDougall\", \"director of\", \"The Weddi... |
[
"Q370244",
"P2175",
"Q12199"
] | [
"Q422631",
"P2175",
"Q12199"
] | [
"Q422631",
"P3780",
"Q29006104"
] | [
"delavirdine",
"medical condition treated",
"HIV/AIDS"
] | [
"lamivudine",
"medical condition treated",
"HIV/AIDS"
] | [
"lamivudine",
"active ingredient in",
"Lamivudine Teva"
] | Q12199__P2175 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting delavirdine, a chemical compound, and a substance that is the active ingredient in Lamivudine Teva? | delavirdine | Lamivudine Teva | active ingredient in | Query: What are different ways of connecting delavirdine, a chemical compound, and a substance that is the active ingredient in Lamivudine Teva?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship, tail) for... | 314 | {"final_response": "<answer>\n{\n \"1\": [\n [\"delavirdine\", \"interacts with\", \"lamivudine\"],\n [\"lamivudine\", \"active ingredient in\", \"Lamivudine Teva\"]\n ],\n \"2\": [\n [\"delavirdine\", \"treats\", \"HIV/AIDS\"],\n [\"HIV/AIDS\", \"treated by\", \"lamivudine\"],\n [\"lamivudine\", \"ac... |
[
"Q190745",
"P166",
"Q38104"
] | [
"Q188128",
"P166",
"Q38104"
] | [
"Q188128",
"P108",
"Q1472245"
] | [
"James Rainwater",
"award received",
"Nobel Prize in Physics"
] | [
"Alexei Abrikosov",
"award received",
"Nobel Prize in Physics"
] | [
"Alexei Abrikosov",
"employer",
"Bauman Moscow State Technical University"
] | Q38104__P166 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting James Rainwater, a notable figure in his field, and someone who has been employed by Bauman Moscow State Technical University? | James Rainwater | Bauman Moscow State Technical University | employer | Query: What are different ways of connecting James Rainwater, a notable figure in his field, and someone who has been employed by Bauman Moscow State Technical University?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (he... | 315 | {"final_response": "```json\n{\n \"1\": [\n [\n \"James Rainwater\",\n \"awarded\",\n \"Nobel Prize in Physics\"\n ],\n [\n \"Nobel Prize in Physics\",\n \"awarded to\",\n \"Vitaly Ginzburg\"\n ],\n [\n \"Vitaly Ginzburg\",\n \"educated at\",\n \"Moscow State... |
[
"Q207191",
"P39",
"Q11699"
] | [
"Q251666",
"P39",
"Q11699"
] | [
"Q251666",
"P26",
"Q525020"
] | [
"John C. Calhoun",
"position held",
"Vice President of the United States"
] | [
"Henry A. Wallace",
"position held",
"Vice President of the United States"
] | [
"Henry A. Wallace",
"spouse",
"Ilo Wallace"
] | Q11699__P39 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting John C. Calhoun, the American politician, and someone who is the spouse of Ilo Wallace? | John C. Calhoun | Ilo Wallace | spouse | Query: What are different ways of connecting John C. Calhoun, the American politician, and someone who is the spouse of Ilo Wallace?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship, tail) forming a conti... | 316 | {"final_response": "<answer>\n{\n \"1\": [\n [\"John C. Calhoun\", \"held office\", \"Vice President of the United States\"],\n [\"Vice President of the United States\", \"office held by\", \"Henry A. Wallace\"],\n [\"Henry A. Wallace\", \"spouse\", \"Ilo Wallace\"]\n ],\n \"2\": [\n [\"John C. Calhoun\"... |
[
"Q125650757",
"P54",
"Q7080909"
] | [
"Q73130120",
"P54",
"Q7080909"
] | [
"Q73130120",
"P413",
"Q622747"
] | [
"Michael Lanese",
"member of sports team",
"Ohio State Buckeyes football"
] | [
"Rod Gerald",
"member of sports team",
"Ohio State Buckeyes football"
] | [
"Rod Gerald",
"position played on team / speciality",
"quarterback"
] | Q7080909__P54 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting Michael Lanese, and someone who played as a quarterback on a team? | Michael Lanese | quarterback | position played on team / speciality | Query: What are different ways of connecting Michael Lanese, and someone who played as a quarterback on a team?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship, tail) forming a continuous chain that begi... | 317 | {"final_response": "<answer>\n{\n \"1\": [\n [\"Michael Lanese\", \"played for\", \"Ohio State Buckeyes football\"],\n [\"Ohio State Buckeyes football\", \"has player\", \"Jim Karsatos\"],\n [\"Jim Karsatos\", \"position played on team / speciality\", \"quarterback\"]\n ],\n \"2\": [\n [\"Michael Lanese\... |
End of preview. Expand in Data Studio
Dataset: connections-dev/connection_queries_jan12
This dataset was generated using the inference script with the following configuration:
Inference Parameters
Model Configuration
- Model Name:
gemini-3.1-pro-preview - Server URL:
Not specified - API Key:
Not provided - Request Timeout:
120 seconds
Query Configuration
- Query Type:
natural - Query Column:
query - Sampling Type:
original
Generation Parameters
- Temperature:
0.7 - Max Tokens:
16384 - Number of Runs:
1 - Chunk Size:
Entire dataset - Effort Level:
medium
Feature Flags
- Step by Step Reasoning:
False - Reasoning Enabled:
False - No Curator:
False - Index Filter:
None (all samples) - Start Index:
300 - End Index:
320
Data Information
- Input File:
connections-dev/connection_queries_jan12 - Number of Samples:
20 - Output Filename:
connection_queries_jan12__natural__s300__e320__original__1__medium__0.7__16384__gemini-3_1-pro-preview.jsonl
Dataset Structure
The dataset contains the following key columns:
query: The original queryentity_a: Starting entityentity_b: Target entityrel_b: Target relationshippath_prediction: Generated connection pathsprompt_for_path: Prompts used for path generation
Usage
You can load this dataset using:
from datasets import load_dataset
dataset = load_dataset("s300_e320_original_1_medium_0.7_16384_gemini-3_1-pro-preview__raw")
Generation Details
This dataset was generated on 2026-03-12 04:32:49 using the inference pipeline with the above configuration.
- Downloads last month
- 11