Triple

T17801102
Position Surface form Disambiguated ID Type / Status
Subject Gloria Foster E444427 entity
Predicate name P16 FINISHED
Object Gloria Foster 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 Foster | Statement: [Gloria Foster, name, Gloria Foster]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gloria Foster
Context triple: [Gloria Foster, name, Gloria Foster]
  • A. Gloria Foster chosen
    Gloria Foster was an American actress best known for her acclaimed stage work and for portraying the Oracle in the first two films of The Matrix trilogy.
  • B. Gloria Gregory
    Gloria Gregory is a character in the film "Goodbye Bafana," which portrays the relationship between Nelson Mandela and his white prison guard during apartheid in South Africa.
  • C. Gloria Gaines
    Gloria Gaines is the wife of longtime White House butler Cecil Gaines in the film "The Butler," serving as a central figure in his personal and family life.
  • D. Gloria Lloyd
    Gloria Lloyd is the daughter of legendary silent film comedian Harold Lloyd and was part of his prominent Hollywood family.
  • E. Gloria Millington
    Gloria Millington is a fictional character from the "Kingdom" series, known for her role within its dramatic, character-driven storyline.
  • 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_69d8b9efe370819095cd219b143ae727 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e487ff42108190b82ceb4466aa2dff completed April 19, 2026, 7:45 a.m.
Created at: April 10, 2026, 10:13 a.m.