Triple

T9538241
Position Surface form Disambiguated ID Type / Status
Subject Howard Hawks E230075 entity
Predicate spouse P13 FINISHED
Object Nancy Gross E230075 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: Nancy Gross | Statement: [Howard Hawks, spouse, Nancy Gross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nancy Gross
Context triple: [Howard Hawks, spouse, Nancy Gross]
  • A. Nancy Gross chosen
    Nancy Gross was the wife of renowned American film director Howard Hawks.
  • B. Nancy Kruse
    Nancy Kruse is a writer known for her work on the story of the animated film "Encanto."
  • C. Nancy Goodman
    Nancy Goodman is an American diplomat, businesswoman, and philanthropist best known for founding the Susan G. Komen Breast Cancer Foundation.
  • D. Nancy Walters
    Nancy Walters was an American model and film and television actress active in the 1950s and early 1960s, known for roles in Hollywood productions including the Elvis Presley musical "Blue Hawaii."
  • E. Nancy Mygatt
    Nancy Mygatt was the first wife of American actor James Whitmore, with whom she had three sons before their divorce.
  • 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_69ca847b1b3081908f72bc932c17cc41 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd98cfead8819089a8f47ea83500a4 completed April 1, 2026, 10:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69f416ab88e48190b3089caab7987191 completed May 1, 2026, 2:57 a.m.
Created at: March 30, 2026, 8:01 p.m.