Triple

T12806439
Position Surface form Disambiguated ID Type / Status
Subject Haller E306154 entity
Predicate hasNotableBearer P458 FINISHED
Object Ernest Haller E62449 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: Ernest Haller | Statement: [Haller, hasNotableBearer, Ernest Haller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ernest Haller
Context triple: [Haller, hasNotableBearer, Ernest Haller]
  • A. Ernest Haller chosen
    Ernest Haller was an American cinematographer best known for his Academy Award-winning work on the classic film "Gone with the Wind."
  • B. Jules Eichorn
    Jules Eichorn was an American mountaineer and early Sierra Nevada climbing pioneer known for significant first ascents in California.
  • C. Maurice Bernhardt
    Maurice Bernhardt was the son of famed French actress Sarah Bernhardt and a French writer and playwright in his own right.
  • D. Frank Barhydt
    Frank Barhydt is an American screenwriter best known for his collaborations with director Robert Altman, including co-writing the acclaimed ensemble film "Short Cuts."
  • E. Gerard Gordeau
    Gerard Gordeau is a Dutch Savate and Kyokushin karate fighter best known as a finalist in the inaugural UFC tournament and for his controversial, highly aggressive fighting style.
  • 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_69d7bdf366888190a8cccb982606889c completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96e7f370c8190b3fc39c1b63394c6 completed April 10, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a544badc8190877c39728e57af6f completed May 3, 2026, 1:30 a.m.
Created at: April 9, 2026, 5:31 p.m.