Triple

T17332283
Position Surface form Disambiguated ID Type / Status
Subject Possession (1981 film) E420845 entity
Predicate editor P1954 FINISHED
Object Marie-Sophie Dubus 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: Marie-Sophie Dubus | Statement: [Possession (1981 film), editor, Marie-Sophie Dubus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marie-Sophie Dubus
Context triple: [Possession (1981 film), editor, Marie-Sophie Dubus]
  • A. Marie-Sophie Dubus chosen
    Marie-Sophie Dubus is a film editor best known for her work on Orson Welles’s experimental documentary "F for Fake."
  • B. Delphine Delaporte
    Delphine Delaporte is known as the spouse of French business executive Thierry Delaporte, the CEO of Wipro.
  • C. Léonore Baulac
    Léonore Baulac is a French ballet dancer and étoile (principal) of the Paris Opera Ballet, acclaimed for her artistry and leading roles in the classical and contemporary repertoire.
  • D. Marie Dubois
    Marie Dubois was a French actress best known for her roles in New Wave cinema, particularly in films directed by François Truffaut.
  • E. Marie-Julie Baup
    Marie-Julie Baup is a French actress known for her work in film, television, and theater.
  • 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_69d889d3adc881909319f1edb8d2a956 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a0fa57881909071fd395b3d46c4 completed April 19, 2026, 2:12 a.m.
Created at: April 10, 2026, 5:43 a.m.