Triple

T21965907
Position Surface form Disambiguated ID Type / Status
Subject Jean-Paul Rappeneau E542455 entity
Predicate directed P7373 FINISHED
Object Tout feu, tout flamme 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: Tout feu, tout flamme | Statement: [Jean-Paul Rappeneau, directed, Tout feu, tout flamme]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tout feu, tout flamme
Context triple: [Jean-Paul Rappeneau, directed, Tout feu, tout flamme]
  • A. Tout feu, tout flamme chosen
    Tout feu, tout flamme is a 1982 French comedy film directed by Jean-Paul Rappeneau, known for its fast-paced farce and energetic performances.
  • B. Allumer le feu
    "Allumer le feu" is a popular rock song by French singer Johnny Hallyday, known as one of his signature anthems performed energetically in concert.
  • C. Contre-feux
    Contre-feux is a political and philosophical work by Pierre Bourdieu that critiques neoliberalism and explores strategies of social and intellectual resistance.
  • D. Le Feu
    Le Feu is a seminal anti-war novel by Henri Barbusse that vividly depicts the grim realities of French soldiers’ experiences in the trenches during World War I.
  • E. L’Incendie
    L’Incendie is a French-language song by Vanessa Paradis from her 2007 pop album "Divinidylle."
  • 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_69e0c47fab1081908dc74a6545dbb051 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1245aabf88190a44564e6eaaa94ce completed April 28, 2026, 9:19 p.m.
Created at: April 16, 2026, 8:01 p.m.