Triple

T22065247
Position Surface form Disambiguated ID Type / Status
Subject George Jay Gould E545250 entity
Predicate child P120 FINISHED
Object Gloria Gould 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: Gloria Gould | Statement: [George Jay Gould, child, Gloria Gould]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gloria Gould
Context triple: [George Jay Gould, child, Gloria Gould]
  • A. Gloria Gould chosen
    Gloria Gould was an American socialite and heiress of the prominent Gould family, known for her role in early 20th-century high society.
  • B. Gloria Talbott
    Gloria Talbott was an American film and television actress known for her roles in 1950s melodramas and science fiction films.
  • C. Lois Gould
    Lois Gould was an American novelist and feminist writer known for her sharp social commentary on gender roles and contemporary relationships.
  • D. Marjorie Weaver
    Marjorie Weaver was an American film actress of the 1930s and 1940s, known for her roles in Hollywood studio productions including several notable dramas and comedies.
  • E. Mildred Gordon
    Mildred Gordon was an American screenwriter best known for her work on mid-20th-century Hollywood films, including family-oriented comedies.
  • 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_69e11e344dfc81909b1d88a7221329c7 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12882ab3c819095b61e0a341edfdf completed April 28, 2026, 9:37 p.m.
Created at: April 16, 2026, 8:27 p.m.