Triple

T21919437
Position Surface form Disambiguated ID Type / Status
Subject Après vous... E541262 entity
Predicate editedBy P1954 FINISHED
Object Isabelle Devinck 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: Isabelle Devinck | Statement: [Après vous..., editedBy, Isabelle Devinck]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isabelle Devinck
Context triple: [Après vous..., editedBy, Isabelle Devinck]
  • A. Isabelle Devinck chosen
    Isabelle Devinck is a French film editor known for her work on the movie "Cible émouvante."
  • B. Jeannette Vermeersch
    Jeannette Vermeersch was a prominent French communist politician and trade unionist who played a leading role in the French Communist Party and the women’s movement in the mid-20th century.
  • C. Maria Pypelinckx
    Maria Pypelinckx was the mother of the Flemish Baroque painter Peter Paul Rubens and thus an in-law relative of his first wife, Isabella Brant.
  • D. Tia Hellebaut
    Tia Hellebaut is a Belgian high jumper best known for winning the gold medal at the 2008 Beijing Olympic Games.
  • E. Eugenie Krekelberg
    Eugenie Krekelberg is best known as the longtime wife and partner of former Dutch Prime Minister Dries van Agt.
  • 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_69e0c47c4b9c8190a5586a75f5f36453 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f12339d88881909e726c9b081bd177 completed April 28, 2026, 9:14 p.m.
Created at: April 16, 2026, 7:44 p.m.