Triple

T16515231
Position Surface form Disambiguated ID Type / Status
Subject Travers Stakes E401164 entity
Predicate firstWinner P11366 FINISHED
Object Kentucky (horse)
Kentucky was a 19th-century American Thoroughbred racehorse best known for winning the inaugural Travers Stakes.
E1218926 NE FINISHED

How this triple was built (4 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: Kentucky (horse) | Statement: [Travers Stakes, firstWinner, Kentucky (horse)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kentucky (horse)
Context triple: [Travers Stakes, firstWinner, Kentucky (horse)]
  • A. Frankel
    Frankel is a legendary, unbeaten British Thoroughbred racehorse widely regarded as one of the greatest racehorses of all time.
  • B. Frankel
    Frankel is the birth surname of American actress and comedian Bea Arthur, best known for her roles in the television series "Maude" and "The Golden Girls."
  • C. Man o’ War
    Man o’ War was a legendary American Thoroughbred racehorse widely regarded as one of the greatest racehorses of all time.
  • D. 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.
  • E. Secretariat
    The Secretariat is the administrative body that supports and coordinates the activities, programs, and decision-implementation of the Indian Ocean Rim Association.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Kentucky (horse)
Triple: [Travers Stakes, firstWinner, Kentucky (horse)]
Generated description
Kentucky was a 19th-century American Thoroughbred racehorse best known for winning the inaugural Travers Stakes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kentucky (horse)
Target entity description: Kentucky was a 19th-century American Thoroughbred racehorse best known for winning the inaugural Travers Stakes.
  • A. Frankel
    Frankel is a legendary, unbeaten British Thoroughbred racehorse widely regarded as one of the greatest racehorses of all time.
  • B. Frankel
    Frankel is the birth surname of American actress and comedian Bea Arthur, best known for her roles in the television series "Maude" and "The Golden Girls."
  • C. Man o’ War
    Man o’ War was a legendary American Thoroughbred racehorse widely regarded as one of the greatest racehorses of all time.
  • D. 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.
  • E. Secretariat
    The Secretariat is the executive administrative body of the Southern African Development Community responsible for coordinating and implementing the organization’s regional policies and programs.
  • F. None of above. chosen

Provenance (5 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_69d883838abc8190bc79cb2d41733ce2 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e7bbfa481909037148cdb4d8996 completed April 18, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a006084949081909e8cdfeafa7564de completed May 10, 2026, 10:40 a.m.
NEDg Description generation batch_6a006322c2f48190aa917f122a33165f completed May 10, 2026, 10:51 a.m.
NED2 Entity disambiguation (via description) batch_6a0063fa6f0c8190906856eb07d80973 completed May 10, 2026, 10:54 a.m.
Created at: April 10, 2026, 5:14 a.m.