Triple

T18574886
Position Surface form Disambiguated ID Type / Status
Subject Laura Poitras E453959 entity
Predicate familyName P18 FINISHED
Object Poitras 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: Poitras | Statement: [Laura Poitras, familyName, Poitras]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Poitras
Context triple: [Laura Poitras, familyName, Poitras]
  • A. Poitras chosen
    Poitras is the surname of Laura Poitras, the American documentary filmmaker known for her work on post-9/11 politics, surveillance, and whistleblowers.
  • B. Gillespi
    Gillespi is a surname, likely a variant of the more common "Gillespie," used by individuals and families of primarily Scottish or Irish origin.
  • C. Rabaut
    Rabaut is a French surname most notably associated with the revolutionary-era politician and Protestant pastor Jean-Paul Rabaut Saint-Étienne.
  • D. Tremblay
    Tremblay is a common French-Canadian surname, particularly prevalent in Quebec and associated with numerous public figures in sports, politics, and the arts.
  • E. Vallière
    Vallière is a river in eastern France that flows through the town of Lons-le-Saunier in the Jura department.
  • 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_69d8d38974308190a9174430ef256b73 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e543c8c0608190afc99235006bf87f completed April 19, 2026, 9:06 p.m.
Created at: April 10, 2026, 11:43 a.m.