Triple

T3715576
Position Surface form Disambiguated ID Type / Status
Subject Frank Gifford E81520 entity
Predicate spouse P13 FINISHED
Object Astrid Lindley E81520 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: Astrid Lindley | Statement: [Frank Gifford, spouse, Astrid Lindley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Astrid Lindley
Context triple: [Frank Gifford, spouse, Astrid Lindley]
  • A. Astrid Lindley chosen
    Astrid Lindley is known as the wife of late Pro Football Hall of Famer and broadcaster Frank Gifford.
  • B. Elizabeth James
    Elizabeth James was the wife of the influential 18th-century Anglican cleric and evangelist George Whitefield, associated with the early Methodist movement and the Great Awakening.
  • C. Helen Murdoch
    Helen Murdoch is a member of the prominent Murdoch family, known primarily as a daughter of influential Australian journalist and media executive Keith Murdoch.
  • D. Margaret Millar
    Margaret Millar was a Canadian-American mystery and suspense novelist renowned for her psychologically complex crime fiction and influential contributions to mid-20th-century detective literature.
  • E. Joan W. Harris
    Joan W. Harris was a Chicago-based philanthropist and arts patron known for her leadership and major contributions to cultural and educational institutions.
  • 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_69ad8b1a81588190b3f27a5483bb610e completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adc9cf77dc819098979094172d82d1 completed March 8, 2026, 7:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4ce0f690c819091d9caf9271f9bbd completed March 14, 2026, 2:55 a.m.
Created at: March 8, 2026, 3:33 p.m.