Triple

T3907601
Position Surface form Disambiguated ID Type / Status
Subject John Mara E87240 entity
Predicate spouse P13 FINISHED
Object Denise Mara E87240 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: Denise Mara | Statement: [John Mara, spouse, Denise Mara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Denise Mara
Context triple: [John Mara, spouse, Denise Mara]
  • A. Denise Mara chosen
    Denise Mara is the wife of New York Giants co-owner John Mara and a member of the prominent Mara family associated with the NFL franchise.
  • B. Denise Richard
    Denise Richard is the mother of Martin Richard, the young boy who was killed in the 2013 Boston Marathon bombing.
  • C. Denisia Andrews
    Denisia Andrews is a contemporary songwriter best known for co-writing major R&B and pop hits, including Beyoncé’s song “Cuff It.”
  • D. Deanna Rose
    Deanna Rose was a local figure in Overland Park, Kansas, whose memory is honored through the Deanna Rose Children’s Farmstead, a popular educational farm and family attraction.
  • E. Marilou York
    Marilou York is an American dental hygienist best known as the longtime wife of actor Mark Hamill.
  • 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_69aed9424514819086e9c58adde6652d completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeed13bb14819096842c6c82342524 completed March 9, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69b562821c3c81909805cb877288405b completed March 14, 2026, 1:28 p.m.
Created at: March 9, 2026, 3:22 p.m.