Triple

T22916476
Position Surface form Disambiguated ID Type / Status
Subject Farewell to the King E568745 entity
Predicate basedOnAuthor P2806 FINISHED
Object Pierre Schoendoerffer 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: Pierre Schoendoerffer | Statement: [Farewell to the King, basedOnAuthor, Pierre Schoendoerffer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pierre Schoendoerffer
Context triple: [Farewell to the King, basedOnAuthor, Pierre Schoendoerffer]
  • A. Pierre Schoendoerffer chosen
    Pierre Schoendoerffer was a French filmmaker, screenwriter, and novelist renowned for his realistic war films, particularly about the Indochina and Vietnam conflicts.
  • B. Stéphane Brizé
    Stéphane Brizé is a French film director and screenwriter known for his socially conscious, realist dramas exploring working-class life and moral dilemmas.
  • C. Michel Aumont
    Michel Aumont was a renowned French actor celebrated for his prolific career in theatre, film, and television, particularly for his character roles and long association with the Comédie-Française.
  • D. Xavier Bresson
    Xavier Bresson is a computer scientist and researcher known for his contributions to graph neural networks, deep learning on irregular domains, and applications in computer vision and network analysis.
  • E. Jean-Jacques Beineix
    Jean-Jacques Beineix was a French film director and key figure of the 1980s "cinéma du look" movement, best known for visually stylish works such as "Diva" and "Betty Blue."
  • 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_69e2458d90c88190a58cead4e781ca6a completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1807a14648190b5d5f7d926f19320 completed April 29, 2026, 3:52 a.m.
Created at: April 17, 2026, 3:42 p.m.