Triple

T2815108
Position Surface form Disambiguated ID Type / Status
Subject Perrin E54262 entity
Predicate hasNotableBearer P458 FINISHED
Object Jean-Michel Perrin
Jean-Michel Perrin is a notable individual who bears the French surname Perrin, recognized enough to be specifically cited among its prominent holders.
E321831 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: Jean-Michel Perrin | Statement: [Perrin, hasNotableBearer, Jean-Michel Perrin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jean-Michel Perrin
Context triple: [Perrin, hasNotableBearer, Jean-Michel Perrin]
  • A. Jean-Claude Perrin
    Jean-Claude Perrin is a French former pole vaulter and athletics coach known for his contributions to French track and field.
  • B. Jean-Paul Perrin
    Jean-Paul Perrin is a relatively obscure individual known primarily from name-bearing records, with no widely documented public achievements or biographical details.
  • C. Jean-Marc Perrin
    Jean-Marc Perrin is a person notable enough to be recognized as a namesake of the surname Perrin.
  • D. Jean-Pierre Perrin
    Jean-Pierre Perrin is a French mathematician known for his contributions to number theory and arithmetic geometry.
  • E. Jean-Luc Perrin
    Jean-Luc Perrin is a French mathematician known for his contributions to number theory and arithmetic geometry.
  • 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: Jean-Michel Perrin
Triple: [Perrin, hasNotableBearer, Jean-Michel Perrin]
Generated description
Jean-Michel Perrin is a notable individual who bears the French surname Perrin, recognized enough to be specifically cited among its prominent holders.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jean-Michel Perrin
Target entity description: Jean-Michel Perrin is a notable individual who bears the French surname Perrin, recognized enough to be specifically cited among its prominent holders.
  • A. Jean-Claude Perrin
    Jean-Claude Perrin is a French former pole vaulter and athletics coach known for his contributions to French track and field.
  • B. Jean-Paul Perrin
    Jean-Paul Perrin is a relatively obscure individual known primarily from name-bearing records, with no widely documented public achievements or biographical details.
  • C. Jean-Marc Perrin
    Jean-Marc Perrin is a person notable enough to be recognized as a namesake of the surname Perrin.
  • D. Jean-Pierre Perrin
    Jean-Pierre Perrin is a French mathematician known for his contributions to number theory and arithmetic geometry.
  • E. Jean-Luc Perrin
    Jean-Luc Perrin is a French mathematician known for his contributions to number theory and arithmetic geometry.
  • 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_69ab49de0af08190b3da69683be1e728 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abde4d29488190a32461906dd9ea7e completed March 7, 2026, 8:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69b1de83d3008190bfb483e0c1e75700 completed March 11, 2026, 9:28 p.m.
NEDg Description generation batch_69b1e4ce2a7081909e46ee6c3307c367 completed March 11, 2026, 9:55 p.m.
NED2 Entity disambiguation (via description) batch_69b1e8bc6a8c8190b148efd3ddbca139 completed March 11, 2026, 10:12 p.m.
Created at: March 6, 2026, 9:59 p.m.