Triple

T18502380
Position Surface form Disambiguated ID Type / Status
Subject Gloria Blondell E452109 entity
Predicate name P16 FINISHED
Object Gloria Blondell 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 Blondell | Statement: [Gloria Blondell, name, Gloria Blondell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gloria Blondell
Context triple: [Gloria Blondell, name, Gloria Blondell]
  • A. Gloria Blondell chosen
    Gloria Blondell was an American film, radio, and television actress of the mid-20th century, known for her character roles and as the younger sister of actress Joan Blondell.
  • B. Gloria Swenson
    Gloria Swenson is the tough, streetwise former mob moll who becomes an unlikely protector of a young boy in the crime thriller film "Gloria."
  • C. Gloria Connors
    Gloria Connors was an American tennis coach best known as the mother and early mentor of tennis champion Jimmy Connors.
  • D. Gloria Millington
    Gloria Millington is a fictional character from the "Kingdom" series, known for her role within its dramatic, character-driven storyline.
  • E. Gloria Rand
    Gloria Rand is a Canadian actress best known as the first wife of actor William Shatner.
  • 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_69d8d3855d50819097fc8561b0299dd9 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e532c535908190bdc90c58fc5bdaf7 completed April 19, 2026, 7:53 p.m.
Created at: April 10, 2026, 11:36 a.m.