Triple

T23464849
Position Surface form Disambiguated ID Type / Status
Subject Rust and Bone E569076 entity
Predicate cinematographyBy P1953 FINISHED
Object Stéphane Fontaine 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: Stéphane Fontaine | Statement: [Rust and Bone, cinematographyBy, Stéphane Fontaine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stéphane Fontaine
Context triple: [Rust and Bone, cinematographyBy, Stéphane Fontaine]
  • A. Stéphane Fontaine chosen
    Stéphane Fontaine is a French cinematographer known for his acclaimed work on contemporary European cinema, including collaborations with prominent auteurs.
  • B. Gilles Mimouni
    Gilles Mimouni is a French filmmaker best known for writing and directing the romantic thriller film "L'Appartement."
  • C. Didier Malherbe
    Didier Malherbe is a French musician and multi-instrumentalist best known as the saxophonist and flautist for the progressive/psychedelic rock band Gong.
  • D. Jean-François Podevin
    Jean-François Podevin is an illustrator and cover artist known for his work on science fiction and fantasy book covers.
  • E. Jean Villepique
    Jean Villepique is an American actress and comedian known for her work on television series such as A.P. Bio and her performances with The Second City.
  • 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_69e2458ebd808190b3298163132cfb0b completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a6f9e59081909e8cf224ee46109c completed April 29, 2026, 6:36 a.m.
Created at: April 17, 2026, 5:54 p.m.