Triple

T15674131
Position Surface form Disambiguated ID Type / Status
Subject Frank Cross E377391 entity
Predicate hasAssistant P30538 FINISHED
Object Grace Cooley E377393 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: Grace Cooley | Statement: [Frank Cross, hasAssistant, Grace Cooley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grace Cooley
Context triple: [Frank Cross, hasAssistant, Grace Cooley]
  • A. Grace Cooley chosen
    Grace Cooley is the compassionate and overworked assistant to Bill Murray’s character in the 1988 Christmas comedy film "Scrooged."
  • B. Sara B. Cooper
    Sara B. Cooper is a screenwriter best known for her work on the film "Lara Croft: Tomb Raider."
  • C. Alice Cooney
    Alice Cooney was the wife of Irish revolutionary and politician Seán Mac Eoin.
  • D. Grace Gealey
    Grace Gealey is a Caymanian-American actress best known for her role as Anika Calhoun on the television series "Empire."
  • E. Mary Leddy
    Mary Leddy was the wife of American labor union official and alleged mob hitman Frank Sheeran, whose life inspired the film "The Irishman."
  • 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_69d85cd2e28481909d4e975bee20872f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04f2c996c8190a9ebe0e92608feaa completed April 16, 2026, 2:53 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0167369d9481909015c34d475fac14 completed May 11, 2026, 5:20 a.m.
Created at: April 10, 2026, 4:16 a.m.