Triple

T21956708
Position Surface form Disambiguated ID Type / Status
Subject Avatar 3 E542206 entity
Predicate stars P1956 FINISHED
Object Sigourney Weaver 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: Sigourney Weaver | Statement: [Avatar 3, stars, Sigourney Weaver]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sigourney Weaver
Context triple: [Avatar 3, stars, Sigourney Weaver]
  • A. Sigourney Weaver chosen
    Sigourney Weaver is an acclaimed American actress best known for her iconic role as Ellen Ripley in the "Alien" film series and her influential work in science fiction and genre cinema.
  • B. Linda Hamilton
    Linda Hamilton is an American actress best known for her iconic role as Sarah Connor in the "Terminator" film series.
  • C. Sigourney Street
    Sigourney Street is a notable thoroughfare in the Asylum Hill neighborhood of Hartford, Connecticut, known for its mix of residential, institutional, and historic buildings.
  • D. Sean Young
    Sean Young is an American actress best known for her roles in 1980s films such as "Blade Runner," "Dune," and "No Way Out."
  • E. Alexandra Hedison
    Alexandra Hedison is an American photographer, director, and former actress known for her contemporary art photography and her work on the television series "The L Word."
  • 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_69e0c47ef0e48190a50e1bcc43f4b3fd completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f124404f38819080bae736a52a51cd completed April 28, 2026, 9:18 p.m.
Created at: April 16, 2026, 7:59 p.m.