Triple

T9030535
Position Surface form Disambiguated ID Type / Status
Subject Colonel Andrew Hynes E216155 entity
Predicate spouse P13 FINISHED
Object Elizabeth Hynes E788095 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: Elizabeth Hynes | Statement: [Colonel Andrew Hynes, spouse, Elizabeth Hynes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth Hynes
Context triple: [Colonel Andrew Hynes, spouse, Elizabeth Hynes]
  • A. Elizabeth Hynes chosen
    Elizabeth Hynes was an early settler and prominent local figure after whom the city of Elizabethtown, Kentucky, was named.
  • B. Elizabeth O'Hara
    Elizabeth O'Hara is best known as the wife of Irish film producer and screenwriter Kevin McClory, who was closely associated with the James Bond franchise.
  • C. Mary Heneghan
    Mary Heneghan is best known as the wife of renowned British broadcaster and talk show host Michael Parkinson.
  • D. Martha Hennessy
    Martha Hennessy is an American Catholic peace activist and granddaughter of Dorothy Day, known for her involvement in the Catholic Worker Movement and anti-nuclear protests.
  • E. Emily Lynch
    Emily Lynch is an Irish woman best known as the sister of actress Evanna Lynch, who played Luna Lovegood in the Harry Potter film series.
  • 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_69ca83a5fa88819088144801b4dd7245 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6a9e0aa881908886f453c51ecd0e completed April 1, 2026, 12:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69d100aef084819086c68bf539343555 completed April 4, 2026, 12:14 p.m.
Created at: March 30, 2026, 7:08 p.m.