Triple

T1903363
Position Surface form Disambiguated ID Type / Status
Subject Société d’Anthropologie de Paris E37742 entity
Predicate notableFounder P22 FINISHED
Object Paul Broca E5993 NE FINISHED

How this triple was built (2 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: Paul Broca | Statement: [Société d’Anthropologie de Paris, notableFounder, Paul Broca]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Broca
Context triple: [Société d’Anthropologie de Paris, notableFounder, Paul Broca]
  • A. Paul Broca chosen
    Paul Broca was a 19th-century French physician, anatomist, and anthropologist best known for discovering the brain region responsible for speech production, now called Broca's area.
  • B. André Broca
    André Broca was a 19th-century French physician and anatomist known for his contributions to the study of the nervous system and pathology.
  • C. José Broca
    José Broca was a 19th-century Spanish classical guitarist and composer known for his refined salon-style guitar works.
  • D. Philippe de Broca
    Philippe de Broca was a French film director best known for his witty, adventurous comedies and collaborations with stars like Jean-Paul Belmondo during the 1960s and 1970s.
  • E. de Broca
    De Broca is the surname of Philippe de Broca, a notable French film director known for his lively adventure comedies and romantic films.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a8861be7148190a680937ec451a304 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb1909aec8190b3259c8f969ce81e completed March 7, 2026, 5:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae3042bdf08190bf43c9246fcc114e completed March 9, 2026, 2:28 a.m.
Created at: March 4, 2026, 7:35 p.m.