Triple

T19152666
Position Surface form Disambiguated ID Type / Status
Subject Dick Vet E468847 entity
Predicate hasFacility P105 FINISHED
Object Equine Hospital 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: Equine Hospital | Statement: [Dick Vet, hasFacility, Equine Hospital]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Equine Hospital
Context triple: [Dick Vet, hasFacility, Equine Hospital]
  • A. Equine Hospital chosen
    Equine Hospital is a specialized veterinary facility dedicated to the medical and surgical care of horses.
  • B. Paraneck Stable
    Paraneck Stable is a Thoroughbred racehorse ownership and breeding operation known for campaigning top-level horses such as Unbridled's Song.
  • C. National Research Centre on Equines
    The National Research Centre on Equines is an Indian premier institute dedicated to research, development, and health management of horses and other equines.
  • D. Haga Stables
    Haga Stables is a historic royal stable building within the Haga Park palace complex in Stockholm, Sweden.
  • E. Stonestreet Stables
    Stonestreet Stables is a prominent American Thoroughbred racing and breeding operation best known for campaigning elite racehorses such as Curlin.
  • 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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e97dc5a481909a58416126a0862d completed April 20, 2026, 8:53 a.m.
Created at: April 10, 2026, 12:06 p.m.