Triple

T17790304
Position Surface form Disambiguated ID Type / Status
Subject Claire Cleary E444140 entity
Predicate sister P14414 FINISHED
Object Gloria Cleary 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 Cleary | Statement: [Claire Cleary, sister, Gloria Cleary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gloria Cleary
Context triple: [Claire Cleary, sister, Gloria Cleary]
  • A. Gloria Cleary chosen
    Gloria Cleary is a quirky, emotionally intense love interest portrayed by Isla Fisher in the comedy film "Wedding Crashers."
  • B. Eileen Connolly
    Eileen Connolly is a prominent author and teacher in the field of tarot and esoteric studies, known for her influential books on divination and metaphysics.
  • C. Kathleen Cleary
    Kathleen Cleary is the wife of Secretary William Cleary, a character in the film "Wedding Crashers."
  • D. Maureen Brady
    Maureen Brady is one of the sisters of former NFL quarterback Tom Brady and a member of the Brady family known for its strong athletic background.
  • E. Maureen Murphy
    Maureen Murphy is a precocious and imaginative young girl who is one of the central members of the dysfunctional Murphy family in the animated comedy series "F Is for Family."
  • 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_69e4879688908190a5428b1fa7525f62 completed April 19, 2026, 7:43 a.m.
Created at: April 10, 2026, 10:13 a.m.