Triple

T20909000
Position Surface form Disambiguated ID Type / Status
Subject Dominique Demers E514884 entity
Predicate birthName P65 FINISHED
Object Dominique Demers 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: Dominique Demers | Statement: [Dominique Demers, birthName, Dominique Demers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dominique Demers
Context triple: [Dominique Demers, birthName, Dominique Demers]
  • A. Dominique Demers chosen
    Dominique Demers is a Canadian author and former journalist best known for her popular children's and young adult books, including the "Mlle Charlotte" series.
  • B. Dominique Fortin
    Dominique Fortin is a film editor best known for her work on major feature films, including the James Bond movie "Tomorrow Never Dies."
  • C. Dominique Bourgeois
    Dominique Bourgeois is a Canadian journalist and the former wife of musician Robbie Robertson, known for her work in media and her connection to the rock group The Band’s inner circle.
  • D. Yvon Demers
    Yvon Demers is a Canadian politician known for serving as a member of the National Assembly of Quebec.
  • E. Valérie Lalonde
    Valérie Lalonde is a French filmmaker and collaborator known for her work in cinéma vérité and her long creative and personal partnership with documentary pioneer Richard Leacock.
  • 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_69e0b4f8a1108190bce3d31331290ced completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e901ca50819080b123af7977efbd completed April 21, 2026, 3:03 a.m.
Created at: April 16, 2026, 12:48 p.m.