Triple

T23461455
Position Surface form Disambiguated ID Type / Status
Subject Carla Brody E568986 entity
Predicate portrayedBy P1507 FINISHED
Object Lorraine Gary 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: Lorraine Gary | Statement: [Carla Brody, portrayedBy, Lorraine Gary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lorraine Gary
Context triple: [Carla Brody, portrayedBy, Lorraine Gary]
  • A. Lorraine Gary chosen
    Lorraine Gary is an American actress best known for playing Ellen Brody in the Jaws film series.
  • B. Lorraine Toussaint
    Lorraine Toussaint is a Trinidadian-American actress known for her powerful performances in film and television, including acclaimed roles in projects like "Orange Is the New Black" and numerous independent dramas.
  • C. Gena Lee Nolin
    Gena Lee Nolin is an American actress and model best known for her role as Neely Capshaw on the television series Baywatch.
  • D. Kathlyn Williams
    Kathlyn Williams was a pioneering American silent film actress best known for her work in early adventure serials and melodramas.
  • E. Linda Rambis
    Linda Rambis is an American basketball executive and longtime Los Angeles Lakers executive director of special projects, known for her influential behind-the-scenes role in the organization.
  • 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_69e2458ebd808190b3298163132cfb0b completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a69bc200819096ed2baf25cdee4f completed April 29, 2026, 6:35 a.m.
Created at: April 17, 2026, 5:53 p.m.