Triple

T22301116
Position Surface form Disambiguated ID Type / Status
Subject Maria Mauban E551257 entity
Predicate notableWork P4 FINISHED
Object César et Rosalie NE NERFINISHED

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: César et Rosalie | Statement: [Maria Mauban, notableWork, César et Rosalie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: César et Rosalie
Context triple: [Maria Mauban, notableWork, César et Rosalie]
  • A. César and Rosalie chosen
    César and Rosalie is a 1972 French romantic drama film directed by Claude Sautet that explores a complex love triangle and is regarded as a classic of intimate, character-driven French cinema.
  • B. La Cézille
    La Cézille is a small locality within the Swiss municipality of Saint-Cergue in the canton of Vaud.
  • C. Pierre et Jean
    Pierre et Jean is a psychological realist novel by Guy de Maupassant that explores family tensions, jealousy, and identity in late 19th-century France.
  • D. Les Dirouilles
    Les Dirouilles is a small group of rocky islets and reefs in the Channel Islands, lying off the coast of Jersey in the English Channel.
  • E. Le Romain
    Le Romain is the nickname of Pierre Mignard, a prominent 17th-century French painter celebrated for his portraits and religious works.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e46c0188190800181a4233f28fe completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f157245ee481909a7a3397de3ae355 completed April 29, 2026, 12:56 a.m.
Created at: April 16, 2026, 8:41 p.m.