Triple

T22481837
Position Surface form Disambiguated ID Type / Status
Subject Bella Crawford E555784 entity
Predicate portrayedBy P1507 FINISHED
Object Gina Torres 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: Gina Torres | Statement: [Bella Crawford, portrayedBy, Gina Torres]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gina Torres
Context triple: [Bella Crawford, portrayedBy, Gina Torres]
  • A. Gina Torres chosen
    Gina Torres is an American actress known for her roles in television series such as "Suits," "Firefly," and "Hannibal."
  • B. Celeste Van Dien
    Celeste Van Dien is the daughter of American actress Catherine Oxenberg and actor Casper Van Dien.
  • C. Amy Acker
    Amy Acker is an American actress best known for her roles in television series such as "Angel," "Person of Interest," and "Dollhouse."
  • D. Carla Gugino
    Carla Gugino is an American actress known for her versatile film and television roles, including prominent performances in projects like "Spy Kids," "Sin City," and "The Haunting of Hill House."
  • E. Zoie Palmer
    Zoie Palmer is a Canadian actress best known for her genre television roles, including prominent parts in sci-fi series such as Dark Matter and Lost Girl.
  • 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_69e11e53897c819088863779f8c50bb0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15c397b248190b36c2fbfa6489693 completed April 29, 2026, 1:17 a.m.
Created at: April 16, 2026, 8:49 p.m.