Datasets:

connections-dev
/

connection_queries_jan12_natural_verbalized_1_medium_0.7_4096_claude-haiku-4-5-20251001_v2

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 8 19	keep_triple bool 1 class	query_prompt stringlengths 3.23k 3.36k	query stringlengths 85 226	entity_a stringlengths 3 55	entity_b stringlengths 4 85	rel_b stringclasses 88 values	index int64 0 930	prompt stringlengths 4.26k 4.48k	path_prediction listlengths 1 1	prompt_for_path listlengths 1 1	all_response_tokens listlengths 1 1	all_reasoning_tokens listlengths 1 1
[ "Q1352656", "P166", "Q935843" ]	[ "Q356715", "P166", "Q935843" ]	[ "Q356715", "P358", "Q100871850" ]	[ "Morton Gould", "award received", "Grammy Lifetime Achievement Award" ]	[ "Benny Carter", "award received", "Grammy Lifetime Achievement Award" ]	[ "Benny Carter", "discography", "Benny Carter discography" ]	Q935843__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 Morton Gould, the American composer and conductor, and someone who has a notable discography in the music industry?	Morton Gould	Benny Carter discography	discography	0	Query: What are different ways of connecting Morton Gould, the American composer and conductor, and someone who has a notable discography in the music 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, relatio...	[ "<think>\nThis is a challenging task. I need to find connection paths from Morton Gould (American composer and conductor) to \"Benny Carter discography\" where the last triple must have the relationship \"discography\" and tail entity \"Benny Carter discography\".\n\nLet me think about what I know:\n- Morton Gould ...	[ "Query: What are different ways of connecting Morton Gould, the American composer and conductor, and someone who has a notable discography in the music industry?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, ...	[ 1864 ]	[ null ]
[ "Q57067", "P166", "Q38104" ]	[ "Q131729", "P166", "Q38104" ]	[ "Q131729", "P106", "Q593644" ]	[ "Max von Laue", "award received", "Nobel Prize in Physics" ]	[ "William Lawrence Bragg", "award received", "Nobel Prize in Physics" ]	[ "William Lawrence Bragg", "occupation", "chemist" ]	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 Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist?	Max von Laue	chemist	occupation	1	Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist? Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual t...	[ "<think>\nLet me think about Max von Laue and find connections to chemists.\n\nMax von Laue (1879-1960) was a German physicist famous for discovering X-ray diffraction in crystals, which won him the Nobel Prize in Physics in 1914.\n\nI need to find paths from Max von Laue to someone whose occupation is \"chemist\"....	[ "Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of fa...	[ 2269 ]	[ null ]
[ "Q2085", "P161", "Q164328" ]	[ "Q2085", "P161", "Q174263" ]	[ "Q174263", "P19", "Q268873" ]	[ "Twin Peaks", "cast member", "David Koechner" ]	[ "Twin Peaks", "cast member", "Rodney Rowland" ]	[ "Rodney Rowland", "place of birth", "Newport Beach" ]	Q2085__P161	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 David Koechner, the American actor and comedian, and someone who was born in Newport Beach?	David Koechner	Newport Beach	place of birth	2	Query: What are different ways of connecting David Koechner, the American actor and comedian, and someone who was born in Newport Beach? 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 c...	[ "<think>Let me think about David Koechner and how to connect him to someone born in Newport Beach.\n\nDavid Koechner is an American actor and comedian, known for roles in:\n- Saturday Night Live\n- Anchorman movies\n- The Office\n- Various other TV shows and movies\n\nNewport Beach is a coastal city in Orange Count...	[ "Query: What are different ways of connecting David Koechner, the American actor and comedian, and someone who was born in Newport Beach?\n\nTask: 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) form...	[ 1297 ]	[ 0 ]
[ "Q18037479", "P2293", "Q11081" ]	[ "Q18053558", "P2293", "Q11081" ]	[ "Q18053558", "P2548", "Q22809711" ]	[ "CD2AP", "genetic association", "Alzheimer's disease" ]	[ "ATXN7L1", "genetic association", "Alzheimer's disease" ]	[ "ATXN7L1", "strand orientation", "reverse strand" ]	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 CD2AP, a protein involved in cellular processes, and a substance that has a reverse strand orientation?	CD2AP	reverse strand	strand orientation	3	Query: What are different ways of connecting CD2AP, a protein involved in cellular processes, and a substance that has a reverse strand orientation? 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)...	[ "<think>\nLet me break down this query:\n\n1. The query asks for connection paths between:\n - Starting entity: CD2AP (a protein involved in cellular processes)\n - Ending condition: A triple with relationship \"strand orientation\" and tail \"reverse strand\"\n\n2. The target condition means the last triple in...	[ "Query: What are different ways of connecting CD2AP, a protein involved in cellular processes, and a substance that has a reverse strand orientation?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship...	[ 2012 ]	[ null ]
[ "Q283572", "P463", "Q254138" ]	[ "Q316136", "P463", "Q254138" ]	[ "Q316136", "P19", "Q39709" ]	[ "Kun Nong", "member of", "Slipknot" ]	[ "Chris Fehn", "member of", "Slipknot" ]	[ "Chris Fehn", "place of birth", "Des Moines" ]	Q254138__P463	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 Kun Nong and someone who was born in Des Moines?	Kun Nong	Des Moines	place of birth	4	Query: What are different ways of connecting Kun Nong and someone who was born in Des Moines? 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 with one entity...	[ "<think>I need to find connections between \"Kun Nong\" and someone who was born in Des Moines, Iowa.\n\nFirst, let me think about who Kun Nong is. I'm not immediately certain about a specific well-known Kun Nong. There could be:\n- A Vietnamese name (Kun Nong sounds like it could be Vietnamese)\n- An Asian musicia...	[ "Query: What are different ways of connecting Kun Nong and someone who was born in Des Moines?\n\nTask: 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 with one...	[ 598 ]	[ 0 ]
[ "Q423327", "P2175", "Q12199" ]	[ "Q422654", "P2175", "Q12199" ]	[ "Q422654", "P769", "Q898407" ]	[ "enfuvirtide", "medical condition treated", "HIV/AIDS" ]	[ "saquinavir", "medical condition treated", "HIV/AIDS" ]	[ "saquinavir", "significant drug interaction", "venlafaxine" ]	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 enfuvirtide, a medication used to treat HIV, and a substance that has a significant drug interaction with venlafaxine?	enfuvirtide	venlafaxine	significant drug interaction	5	Query: What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a substance that has a significant drug interaction with venlafaxine? Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, rela...	[ "<think>\nThis is a complex task requiring me to find connection paths between enfuvirtide and venlafaxine via \"significant drug interaction\" relationships.\n\nFirst, let me establish what we know:\n- Enfuvirtide: an HIV fusion inhibitor medication (a monoclonal antibody-like drug)\n- Venlafaxine: an SNRI antidep...	[ "Query: What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a substance that has a significant drug interaction with venlafaxine?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (hea...	[ 1867 ]	[ null ]
[ "Q77462", "P463", "Q32645" ]	[ "Q95556", "P463", "Q32645" ]	[ "Q95556", "P451", "Q551050" ]	[ "Bela B", "member of", "Die Ärzte" ]	[ "Hagen Liebing", "member of", "Die Ärzte" ]	[ "Hagen Liebing", "unmarried partner", "Anja Caspary" ]	Q32645__P463	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 Bela B, the German musician, and someone who is the unmarried partner of Hagen Liebing?	Bela B	Anja Caspary	unmarried partner	6	Query: What are different ways of connecting Bela B, the German musician, and someone who is the unmarried partner of Hagen Liebing? 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...	[ "<think>Let me analyze this query carefully. I need to find connection paths between:\n- Start entity: Bela B (German musician)\n- End condition: A path that ends with triple (X, \"unmarried partner\", Anja Caspary)\n\nFirst, let me establish what I know:\n1. Bela B is the lead singer of Die Ärzte, a German punk ro...	[ "Query: What are different ways of connecting Bela B, the German musician, and someone who is the unmarried partner of Hagen Liebing?\n\nTask: 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 ...	[ 1330 ]	[ 0 ]
[ "Q651253", "P40", "Q1268" ]	[ "Q9356382", "P40", "Q1268" ]	[ "Q9356382", "P22", "Q11716498" ]	[ "Nicolas Chopin", "child", "Frédéric Chopin" ]	[ "Tekla Justyna Chopin", "child", "Frédéric Chopin" ]	[ "Tekla Justyna Chopin", "father", "Jakub Krzyżanowski" ]	Q1268__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 Nicolas Chopin, and someone who is the father of Jakub Krzyżanowski?	Nicolas Chopin	Jakub Krzyżanowski	father	7	Query: What are different ways of connecting Nicolas Chopin, and someone who is the father of Jakub Krzyżanowski? 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 be...	[ "<think>This is a challenging query. Let me break down what I need to find:\n\n1. Starting entity: Nicolas Chopin\n2. Target condition: Someone who is the father of Jakub Krzyżanowski\n3. I need to find multiple paths connecting these\n\nFirst, let me identify the entities:\n- Nicolas Chopin: I need to determine wh...	[ "Query: What are different ways of connecting Nicolas Chopin, and someone who is the father of Jakub Krzyżanowski?\n\nTask: 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 ...	[ 665 ]	[ 0 ]
[ "Q23505", "P40", "Q207" ]	[ "Q190628", "P40", "Q207" ]	[ "Q190628", "P39", "Q7166256" ]	[ "George H. W. Bush", "child", "George W. Bush" ]	[ "Barbara Bush", "child", "George W. Bush" ]	[ "Barbara Bush", "position held", "First Lady of the United States" ]	Q207__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 George H. W. Bush, the 41st President of the United States, and someone who held the position of First Lady of the United States?	George H. W. Bush	First Lady of the United States	position held	8	Query: What are different ways of connecting George H. W. Bush, the 41st President of the United States, and someone who held the position of First Lady of the United States? Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples ...	[ "<think>\nLet me think about this systematically. I need to find paths from \"George H. W. Bush\" to someone who held the position of \"First Lady of the United States\".\n\nGeorge H. W. Bush was the 41st President of the United States. His wife was Barbara Bush, who was First Lady from 1989-1993.\n\nSo the most di...	[ "Query: What are different ways of connecting George H. W. Bush, the 41st President of the United States, and someone who held the position of First Lady of the United States?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual t...	[ 1771 ]	[ null ]
[ "Q18037778", "P2293", "Q131755" ]	[ "Q18046338", "P2293", "Q131755" ]	[ "Q18046338", "P5572", "Q64386" ]	[ "INTS7", "genetic association", "bipolar disorder" ]	[ "MCTP1", "genetic association", "bipolar disorder" ]	[ "MCTP1", "expressed in", "gallbladder" ]	Q131755__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 INTS7, a protein involved in various cellular processes, and a substance that is expressed in the gallbladder?	INTS7	gallbladder	expressed in	9	Query: What are different ways of connecting INTS7, a protein involved in various cellular processes, and a substance that is expressed in the gallbladder? 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...	[ "<think>This is a challenging query. Let me break down what's being asked:\n\n1. I need to find connection paths from INTS7 (a protein) to something \"expressed in gallbladder\"\n2. INTS7 is involved in various cellular processes\n3. I need to find what substance/entity is expressed in the gallbladder that connects...	[ "Query: What are different ways of connecting INTS7, a protein involved in various cellular processes, and a substance that is expressed in the gallbladder?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relat...	[ 1582 ]	[ 0 ]
[ "Q47703", "P161", "Q960676" ]	[ "Q47703", "P161", "Q786720" ]	[ "Q786720", "P19", "Q18419" ]	[ "The Godfather", "cast member", "Joe Spinell" ]	[ "The Godfather", "cast member", "Richard Bright" ]	[ "Richard Bright", "place of birth", "Brooklyn" ]	Q47703__P161	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 Joe Spinell, the American actor, and someone who was born in Brooklyn?	Joe Spinell	Brooklyn	place of birth	10	Query: What are different ways of connecting Joe Spinell, the American actor, and someone who was born in Brooklyn? 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 ...	[ "<think>\nLet me think about this carefully. I need to find connection paths from Joe Spinell to someone who was born in Brooklyn.\n\nFirst, let me recall what I know about Joe Spinell:\n- Joe Spinell was an American actor (1946-1989)\n- He was born in Brooklyn, New York\n- He appeared in many films and TV shows\n-...	[ "Query: What are different ways of connecting Joe Spinell, the American actor, and someone who was born in Brooklyn?\n\nTask: 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 chai...	[ 1648 ]	[ null ]

End of preview. Expand in Data Studio

Dataset: connections-dev/connection_queries_jan12_natural_verbalized_1_medium_0.7_4096_claude-haiku-4-5-20251001

This dataset was generated using the inference script with the following configuration:

Inference Parameters

Model Configuration

Model Name: claude-haiku-4-5-20251001
Server URL: Not specified
API Key: Not provided
Request Timeout: 300 seconds

Query Configuration

Query Type: natural
Query Column: query
Sampling Type: verbalized

Generation Parameters

Temperature: 0.7
Max Tokens: 1024
Number of Runs: 1
Chunk Size: Entire dataset
Effort Level: medium

Feature Flags

Step by Step Reasoning: False
Reasoning Enabled: True
No Curator: False
Index Filter: None (all samples)
Start Index: None
End Index: None

Data Information

Input File: connections-dev/connection_queries_jan12_natural_verbalized_1_medium_0.7_4096_claude-haiku-4-5-20251001
Number of Samples: 429
Output Filename: connection_queries_jan12_natural_verbalized_1_medium_0__natural__verbalized__1__reasoning__medium__0.7__1024__claude-haiku-4-5-20251001.jsonl

Dataset Structure

The dataset contains the following key columns:

query: The original query
entity_a: Starting entity
entity_b: Target entity
rel_b: Target relationship
path_prediction: Generated connection paths
prompt_for_path: Prompts used for path generation

Usage

You can load this dataset using:

from datasets import load_dataset

dataset = load_dataset("connections-dev/connection_queries_jan12_natural_verbalized_1_medium_0.7_4096_claude-haiku-4-5-20251001_v2")

Generation Details

This dataset was generated on 2026-01-25 23:20:41 using the inference pipeline with the above configuration.

Downloads last month: 8