Triple

T23339768
Position Surface form Disambiguated ID Type / Status
Subject Taking Lives E591701 entity
Predicate starring P1507 FINISHED
Object Tchéky Karyo 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: Tchéky Karyo | Statement: [Taking Lives, starring, Tchéky Karyo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tchéky Karyo
Context triple: [Taking Lives, starring, Tchéky Karyo]
  • A. Tchéky Karyo chosen
    Tchéky Karyo is a French actor known for his intense character roles in international films and television, including action, drama, and historical epics.
  • B. Roger Karoutchi
    Roger Karoutchi is a French politician and long-serving senator known for his roles in government and leadership within France’s mainstream right.
  • C. Joseph Biroc
    Joseph Biroc was an American cinematographer best known for his influential work on classic Hollywood films, including the beloved holiday movie "It's a Wonderful Life."
  • D. Alain Jomy
    Alain Jomy is a French film composer and music critic known for his scores for European cinema, including collaborations on acclaimed French dramas.
  • E. Jean-Pierre Mocky
    Jean-Pierre Mocky was a French film director, screenwriter, producer, and actor known for his prolific output of offbeat, satirical, and socially critical films from the 1960s onward.
  • 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_69e25d20156c81908c5c53195bd9c738 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f198317f4c8190a557cacb86568d6c completed April 29, 2026, 5:33 a.m.
Created at: April 17, 2026, 5:18 p.m.