Triple

T20390488
Position Surface form Disambiguated ID Type / Status
Subject Angel Heart E498070 entity
Predicate character P662 FINISHED
Object Harry Angel 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: Harry Angel | Statement: [Angel Heart, character, Harry Angel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Angel
Context triple: [Angel Heart, character, Harry Angel]
  • A. Harry Angel chosen
    Harry Angel is a top-class British sprinter racehorse renowned for his Group 1 victories and status as one of the leading sprinters of his generation.
  • B. Baffert
    Baffert is the surname most prominently associated with American Thoroughbred racehorse trainer Bob Baffert, a multiple Kentucky Derby and Triple Crown winner.
  • C. Mr. Prospector
    Mr. Prospector was a highly influential American Thoroughbred racehorse and sire, renowned as one of the most important stallions in modern racing and breeding history.
  • D. Dr. Fager
    Dr. Fager was a legendary American Thoroughbred racehorse renowned for his speed, versatility, and multiple championship titles in the late 1960s.
  • E. Funny Cide
    Funny Cide is an American Thoroughbred racehorse best known for winning the 2003 Kentucky Derby and Preakness Stakes.
  • 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6790f8d9c819093038f6bb6f47a92 completed April 20, 2026, 7:05 p.m.
Created at: April 16, 2026, 11:28 a.m.