Triple

T21473889
Position Surface form Disambiguated ID Type / Status
Subject Les Éditions de Minuit E529802 entity
Predicate founder P104 FINISHED
Object Yvonne Paraf 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: Yvonne Paraf | Statement: [Les Éditions de Minuit, founder, Yvonne Paraf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yvonne Paraf
Context triple: [Les Éditions de Minuit, founder, Yvonne Paraf]
  • A. Yvonne Paraf chosen
    Yvonne Paraf was a French publisher best known as the founder of the influential literary publishing house Les Éditions de Minuit.
  • B. Yvonne Francas
    Yvonne Francas is a British television producer known for her work on popular UK drama series.
  • C. Yvonne Landowski
    Yvonne Landowski was the wife of French sculptor Paul Landowski, known primarily in relation to his life and work.
  • D. Yvonne Pawlett
    Yvonne Pawlett is a British musician best known as an early keyboardist for the influential post-punk band The Fall.
  • E. Yvonne Hartman
    Yvonne Hartman is a high-ranking and ambitious director of the Torchwood Institute in the Doctor Who universe, known for her role in the events leading to a catastrophic interdimensional breach.
  • 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_69e0c459acb481909bb6ee452a0045c7 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea156dac819087c4594d022d3df6 completed April 23, 2026, 9:44 a.m.
Created at: April 16, 2026, 6:19 p.m.