Triple

T13686318
Position Surface form Disambiguated ID Type / Status
Subject Pierre-Louis Lions E328137 entity
Predicate familyName P18 FINISHED
Object Lions
Lions is a common French surname borne by several notable individuals, including the Fields Medal–winning mathematician Pierre-Louis Lions.
E1059455 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Lions | Statement: [Pierre-Louis Lions, familyName, Lions]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lions
Context triple: [Pierre-Louis Lions, familyName, Lions]
  • A. Lions
    Lions is the commonly used short name for the Brisbane Lions, a professional Australian rules football club based in Brisbane that competes in the Australian Football League (AFL).
  • B. Lions
    The Lions are the athletic teams representing Columbia University, most notably its men's basketball program competing in NCAA Division I.
  • C. Lions
    The Lions are the athletic teams representing Lincoln University in Pennsylvania in intercollegiate sports.
  • D. Lions
    The Lions are the athletic teams representing the University of North Alabama in collegiate sports.
  • E. Lions
    The Lions are a professional American football team based in Detroit, Michigan, competing in the National Football League (NFL).
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lions
Triple: [Pierre-Louis Lions, familyName, Lions]
Generated description
Lions is a common French surname borne by several notable individuals, including the Fields Medal–winning mathematician Pierre-Louis Lions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lions
Target entity description: Lions is a common French surname borne by several notable individuals, including the Fields Medal–winning mathematician Pierre-Louis Lions.
  • A. Lions
    Lions is a French surname most notably borne by the influential mathematician and control theorist Jacques-Louis Lions.
  • B. Lions
    Lions is the commonly used short name for the Brisbane Lions, a professional Australian rules football club based in Brisbane that competes in the Australian Football League (AFL).
  • C. Lions
    The Lions are a South African professional rugby union team based in Johannesburg that competes in major domestic and international competitions.
  • D. Lions
    Lions are large, social predatory cats native mainly to Africa, known for their muscular build, manes on males, and role as iconic symbols of strength and courage.
  • E. Lions
    The Lions are a professional American football team based in Detroit, Michigan, competing in the National Football League (NFL).
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8076f1fa8819094664a59b55010df completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc670968881908e2b4fdf656c7285 completed April 12, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7a8416d808190bd9cb77e0dd0d4be completed May 3, 2026, 7:55 p.m.
NEDg Description generation batch_69f7a994cd688190a077a4854c5c71c9 completed May 3, 2026, 8:01 p.m.
NED2 Entity disambiguation (via description) batch_69f7aa2f696081908f48d44bf7271abc completed May 3, 2026, 8:03 p.m.
Created at: April 9, 2026, 9:53 p.m.