Triple

T13313292
Position Surface form Disambiguated ID Type / Status
Subject Max et Jérémie E317127 entity
Predicate screenwriter P2831 FINISHED
Object Claire Devers E1034245 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: Claire Devers | Statement: [Max et Jérémie, screenwriter, Claire Devers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Claire Devers
Context triple: [Max et Jérémie, screenwriter, Claire Devers]
  • A. Claire Devers chosen
    Claire Devers is a French film director and screenwriter known for her intimate, character-driven dramas and exploration of complex human relationships.
  • B. Claire Maurier
    Claire Maurier is a French actress known for her roles in classic films of the French New Wave and a long career in French cinema and television.
  • C. Claire Carleton
    Claire Carleton was an American actress known for her supporting roles in mid-20th-century films, including the 1956 horror movie "The Black Sleep."
  • D. Claire Louise
    Claire Louise was the wife of American film actor Robert Armstrong, best known for his role in the classic movie "King Kong."
  • E. May de Lavergne
    May de Lavergne was an early 20th-century French actress known for appearing in Georges Méliès’s pioneering silent film "The Impossible Voyage."
  • 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_69d806b40ab4819094adf6c374f4811a completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d990f6d34c8190ba19dc2df7d42c22 completed April 11, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7266cfb3c8190ac9ccb7696d02922 completed May 3, 2026, 10:41 a.m.
Created at: April 9, 2026, 9:29 p.m.