Triple

T20734414
Position Surface form Disambiguated ID Type / Status
Subject Michel Simon E509655 entity
Predicate name P16 FINISHED
Object Michel Simon 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: Michel Simon | Statement: [Michel Simon, name, Michel Simon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michel Simon
Context triple: [Michel Simon, name, Michel Simon]
  • A. Michel Simon chosen
    Michel Simon was a renowned Swiss-born French actor celebrated for his expressive character roles in classic European cinema from the 1920s through the 1960s.
  • B. Claude Brasseur
    Claude Brasseur was a prominent French actor known for his versatile performances in film, television, and theater, and as part of a celebrated family of French performers.
  • C. Pierre Fresnay
    Pierre Fresnay was a prominent French stage and film actor known for his refined performances in classics such as "Marius" and "La Grande Illusion."
  • D. Émile Krieps
    Émile Krieps was a prominent Luxembourgish politician and former Resistance member who held several high-ranking government positions, including leadership roles in the national legislature.
  • E. Joseph Noiret
    Joseph Noiret was a Belgian poet, painter, and art critic best known as a founding figure of the postwar avant-garde COBRA movement.
  • 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_69e0b4c589c08190834fb5d86d0efa2b completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c209348c819084a2f35f36378680 completed April 21, 2026, 12:17 a.m.
Created at: April 16, 2026, 12:31 p.m.