Triple

T20621030
Position Surface form Disambiguated ID Type / Status
Subject The Confession E506696 entity
Predicate stars P1956 FINISHED
Object Yves Montand 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: Yves Montand | Statement: [The Confession, stars, Yves Montand]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yves Montand
Context triple: [The Confession, stars, Yves Montand]
  • A. Yves Montand chosen
    Yves Montand was a renowned Italian-French actor and singer celebrated for his roles in classic European cinema and his charismatic musical performances.
  • B. Marcel Darrieux
    Marcel Darrieux was a French violinist known for premiering significant 20th-century violin works.
  • C. Jean-Pierre Aumont
    Jean-Pierre Aumont was a French stage and film actor known for his romantic leading roles in European and Hollywood cinema from the 1930s through the 1960s.
  • D. Jean Marais
    Jean Marais was a renowned French actor, director, and sculptor best known for his collaborations with filmmaker Jean Cocteau and his roles in classic French cinema.
  • E. Anthony Franciosa
    Anthony Franciosa was an American actor known for his intense, charismatic performances in film and television during the 1950s through the 1970s, including notable roles in dramas and crime thrillers.
  • 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_69e0b4bc90988190ac360aaf645efc1d completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6abe19ca481908c896bec49a025cd completed April 20, 2026, 10:42 p.m.
Created at: April 16, 2026, 11:42 a.m.