Triple

T9762890
Position Surface form Disambiguated ID Type / Status
Subject Counterpart E236710 entity
Predicate starring P1507 FINISHED
Object Betty Gabriel E274472 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: Betty Gabriel | Statement: [Counterpart, starring, Betty Gabriel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Betty Gabriel
Context triple: [Counterpart, starring, Betty Gabriel]
  • A. Betty Gabriel chosen
    Betty Gabriel is an American actress best known for her breakout role as the unsettling housekeeper Georgina in the horror film "Get Out."
  • B. Betty Garde
    Betty Garde was an American stage, film, and radio actress known for her versatile character roles in mid-20th-century theater and entertainment.
  • C. Barbara Cassidy
    Barbara Cassidy is the mother of the late American singer and guitarist Eva Cassidy.
  • D. Babs Davy
    Babs Davy is an American theater artist best known as a member of the feminist, queer performance collective The Five Lesbian Brothers.
  • E. Mary Garrard
    Mary Garrard is an American art historian and feminist scholar best known for her influential work on women artists such as Artemisia Gentileschi and for advancing feminist perspectives in art history.
  • 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_69ca84d64f6c8190a4ed4e9f5936eda5 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda09d8bc88190808145f141b4a9f8 completed April 1, 2026, 10:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1bcec777c81908b2eff64f4756517 completed April 5, 2026, 1:37 a.m.
Created at: March 30, 2026, 8:25 p.m.