Triple

T10710976
Position Surface form Disambiguated ID Type / Status
Subject Joan Blondell E252533 entity
Predicate sibling P363 FINISHED
Object Gloria Blondell E452109 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: Gloria Blondell | Statement: [Joan Blondell, sibling, Gloria Blondell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gloria Blondell
Context triple: [Joan Blondell, sibling, 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 Connors
    Gloria Connors was an American tennis coach best known as the mother and early mentor of tennis champion Jimmy Connors.
  • C. Gloria Millington
    Gloria Millington is a fictional character from the "Kingdom" series, known for her role within its dramatic, character-driven storyline.
  • D. Myrna Fahey
    Myrna Fahey was an American actress known for her film and television roles in the 1950s and 1960s, often appearing in comedies and dramas.
  • E. Gloria Greer
    Gloria Greer was an American actress best known for her work in early 20th-century films and for her marriage to film director Alan Crosland.
  • 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_69d6aa5cbabc8190973e683950d89faf completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6fe523de08190a82c8f057fe8baf6 completed April 9, 2026, 1:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69e15478caa88190934fca5448f8a49e completed April 16, 2026, 9:28 p.m.
Created at: April 8, 2026, 9:13 p.m.