Triple

T22707234
Position Surface form Disambiguated ID Type / Status
Subject Joseph Kessel E561488 entity
Predicate notableWork P4 FINISHED
Object Belle de Jour 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: Belle de Jour | Statement: [Joseph Kessel, notableWork, Belle de Jour]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Belle de Jour
Context triple: [Joseph Kessel, notableWork, Belle de Jour]
  • A. Belle de Jour chosen
    Belle de Jour is a 1967 French drama film directed by Luis Buñuel, renowned for its surreal exploration of a bourgeois housewife who secretly works as a high-class prostitute.
  • B. Last Tango in Paris
    Last Tango in Paris is a controversial 1972 erotic drama film directed by Bernardo Bertolucci and starring Marlon Brando and Maria Schneider, noted for its explicit sexual content and psychological intensity.
  • C. Day for Night
    Day for Night is a film-based artwork by British visual artist Tacita Dean that explores light, time, and cinematic perception through her signature analog techniques.
  • D. Day for Night
    Day for Night is a critically acclaimed 1994 rock album by Canadian band The Tragically Hip, noted for its darker, more atmospheric sound and poetic lyrics.
  • E. Day for Night
    Day for Night is a 1973 French meta-film directed by François Truffaut that explores the chaotic, humorous, and emotional process of making a movie.
  • 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_69e2454f1348819088d83f420925a5c1 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f178cff7588190a40c8cef0f3cd44a completed April 29, 2026, 3:19 a.m.
Created at: April 17, 2026, 3:17 p.m.