Triple

T21385163
Position Surface form Disambiguated ID Type / Status
Subject Sandi Graham E527473 entity
Predicate spouse P13 FINISHED
Object Dennis Graham NE NERFINISHED

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: Dennis Graham | Statement: [Sandi Graham, spouse, Dennis Graham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dennis Graham
Context triple: [Sandi Graham, spouse, Dennis Graham]
  • A. Dennis Graham chosen
    Dennis Graham is an American musician and drummer best known as the father of Canadian rapper and singer Drake.
  • B. Gordon Gray
    Gordon Gray is a fictional character from the soap opera "General Hospital," known primarily as the biological father of Laura Webber.
  • C. Gordon Gray
    Gordon Gray is an American film producer known for inspirational sports dramas and family-oriented movies such as "The Rookie" and "Miracle."
  • D. Gordon Gray
    Gordon Gray was an American government official and national security advisor who held several high-level posts under Presidents Truman and Eisenhower, including roles in defense and intelligence policy.
  • E. Dennis Scott
    Dennis Scott is a former American professional basketball player best known as a prolific three-point shooter in the NBA, particularly with the Orlando Magic in the 1990s.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b51f363c8190944000ab5523b02b completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69ee62c9494081909efa74e189454dc6 completed April 26, 2026, 7:08 p.m.
Created at: April 16, 2026, 5:12 p.m.