Triple

T7418580
Position Surface form Disambiguated ID Type / Status
Subject Zoë Kravitz E171187 entity
Predicate relative P37 FINISHED
Object Roxie Roker E161500 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: Roxie Roker | Statement: [Zoë Kravitz, relative, Roxie Roker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roxie Roker
Context triple: [Zoë Kravitz, relative, Roxie Roker]
  • A. Roxie Roker chosen
    Roxie Roker was an American actress best known for her groundbreaking role as Helen Willis, one half of one of television’s first interracial couples, on the sitcom "The Jeffersons."
  • B. Barbara Rush
    Barbara Rush is an American actress best known for her work in mid-20th-century film and television, including prominent roles in dramas and science fiction classics.
  • C. Yvonne De Carlo
    Yvonne De Carlo was a Canadian-American actress and singer best known for her roles in classic Hollywood films and as Lily Munster on the television series "The Munsters."
  • D. Cheryl White
    Cheryl White is a supporting character in the sports drama film "McFarland, USA," depicted as part of the community surrounding the high school cross-country team.
  • E. Betty Garrett
    Betty Garrett was an American actress, comedian, singer, and dancer known for her energetic performances in mid-20th-century Hollywood musicals and later in popular television sitcoms.
  • 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_69c68a625d048190af70eb8b63bec5a0 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f2e93ffc8190beb5a1d3eb6c5d23 completed March 27, 2026, 9:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8344541308190af8d90633cd92645 completed March 28, 2026, 8:04 p.m.
Created at: March 27, 2026, 3:11 p.m.