Triple

T21976280
Position Surface form Disambiguated ID Type / Status
Subject Manon des Sources E542711 entity
Predicate screenwriter P2831 FINISHED
Object Gérard Brach 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: Gérard Brach | Statement: [Manon des Sources, screenwriter, Gérard Brach]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gérard Brach
Context triple: [Manon des Sources, screenwriter, Gérard Brach]
  • A. Gérard Brach chosen
    Gérard Brach was a French screenwriter and frequent Roman Polanski collaborator known for his work on numerous acclaimed European films.
  • B. Gérard Blain
    Gérard Blain was a French actor and film director known for his roles in mid-20th-century European cinema and his later work as a New Wave–adjacent auteur.
  • C. Yve-Alain Bois
    Yve-Alain Bois is a prominent French art historian and critic known for his influential scholarship on 20th-century modernism and abstract art.
  • D. Alain Glavieux
    Alain Glavieux was a French engineer and information theorist best known as a co-inventor of turbo codes, a breakthrough in error-correcting coding that revolutionized digital communications.
  • E. Michel Andrault
    Michel Andrault was a prominent French architect known for his influential large-scale housing and urban development projects in the late 20th century.
  • 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_69e0c48070988190909db97667b9a0ac completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f124886418819091daed0988432350 completed April 28, 2026, 9:20 p.m.
Created at: April 16, 2026, 8:03 p.m.