Triple

T7357052
Position Surface form Disambiguated ID Type / Status
Subject Suits E169651 entity
Predicate portrayedBy P1507 FINISHED
Object Gina Torres E339476 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: Gina Torres | Statement: [Suits, portrayedBy, Gina Torres]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gina Torres
Context triple: [Suits, 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. Karen Rodriguez
    Karen Rodriguez is an actress known for her role in the television series "Swarm."
  • 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_69c68a59f2288190877ca15c19b1e822 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f13a62e48190a2d1781a630aa9f0 completed March 27, 2026, 9:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7faa6a5d88190b969b7783edc67b7 completed March 28, 2026, 3:58 p.m.
Created at: March 27, 2026, 3:06 p.m.