Triple

T22274178
Position Surface form Disambiguated ID Type / Status
Subject Garde à vue E550557 entity
Predicate starring P1507 FINISHED
Object Guy Marchand 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: Guy Marchand | Statement: [Garde à vue, starring, Guy Marchand]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Guy Marchand
Context triple: [Garde à vue, starring, Guy Marchand]
  • A. Guy Marchand chosen
    Guy Marchand is a French actor, singer, and musician known for his prolific film and television career, including notable roles in French cinema classics.
  • B. Paul Marchand
    Paul Marchand is an editor known for his work on the publication "Head of State."
  • C. Jean-Louis Beaudry
    Jean-Louis Beaudry was a 19th-century Canadian businessman and politician who served multiple terms as mayor of Montreal and played a key role in the city’s economic development.
  • D. Yannick Agnel
    Yannick Agnel is a French Olympic and world champion freestyle swimmer known for his dominance in middle-distance events, particularly at the 2012 London Games.
  • E. David Madel
    David Madel is a British Conservative politician who served as a Member of Parliament from the 1970s until the late 1990s.
  • 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_69e11e43d8208190aff4f9cf7f2c2a8a completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f14ea547e4819098baf88f3c605242 completed April 29, 2026, 12:19 a.m.
Created at: April 16, 2026, 8:40 p.m.