Triple

T4579161
Position Surface form Disambiguated ID Type / Status
Subject Laura Poitras E101811 entity
Predicate name P16 FINISHED
Object Laura Poitras E101811 NE FINISHED

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: Laura Poitras | Statement: [Laura Poitras, name, Laura Poitras]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laura Poitras
Context triple: [Laura Poitras, name, Laura Poitras]
  • A. Laura Poitras chosen
    Laura Poitras is an American documentary filmmaker and journalist best known for her work on U.S. surveillance and national security, including the Oscar-winning film "Citizenfour" about Edward Snowden.
  • B. David Pilger
    David Pilger is an individual notable enough to be recorded as a bearer of the surname Pilger, though no widely recognized public information about him is available.
  • C. Jennifer Fox
    Jennifer Fox is an American film and television producer known for her work on acclaimed projects such as the geopolitical thriller "Syriana."
  • D. Jennifer Fox
    Jennifer Fox is an American filmmaker and producer known for her autobiographical drama film "The Tale" and her work in documentary cinema.
  • E. Michael Pilger
    Michael Pilger is an individual notable enough to be specifically cited as a bearer of the surname Pilger.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd43d4ce208190b53158c882b222e3 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd58e3e028819083c4662deb9f3c03 completed March 20, 2026, 2:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69bde09015c48190b4f992f3f95023cf completed March 21, 2026, 12:04 a.m.
Created at: March 20, 2026, 1:10 p.m.