Triple

T12139618
Position Surface form Disambiguated ID Type / Status
Subject Anne Heche E289147 entity
Predicate partner P1136 FINISHED
Object James Tupper E452273 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: James Tupper | Statement: [Anne Heche, partner, James Tupper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: James Tupper
Context triple: [Anne Heche, partner, James Tupper]
  • A. James Tupper chosen
    James Tupper is a Canadian actor best known for his television roles in series such as Men in Trees, Revenge, and Big Little Lies.
  • B. William H. Lubbock
    William H. Lubbock was a Canadian municipal politician who served as mayor of Burnaby, British Columbia.
  • C. William Guest
    William Guest was an American R&B singer best known as a longtime member of the legendary soul group Gladys Knight & the Pips.
  • D. William Guest
    William Guest is the time-traveling narrator of William Morris’s utopian novel "News from Nowhere," through whose eyes readers explore a future socialist society.
  • E. Frederick Lister
    Frederick Lister was a British figure best known as the founder of the Royal British Legion, a major UK charity supporting members and veterans of the British Armed Forces.
  • 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_69d6ab4b5e4c81909950b17151eb0951 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d9158eef48819083bdce283a363414 completed April 10, 2026, 3:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f692ee048190ab42c92296fd28fb completed May 2, 2026, 1:05 p.m.
Created at: April 8, 2026, 9:49 p.m.