Triple

T18320123
Position Surface form Disambiguated ID Type / Status
Subject American Horse of the Year E438850 entity
Predicate geographicFocus P82 FINISHED
Object United States Thoroughbred racing season
The United States Thoroughbred racing season is the annual calendar of major flat races and stakes events in American horse racing, culminating in prestigious awards and championships.
E1317811 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: United States Thoroughbred racing season | Statement: [American Horse of the Year, geographicFocus, United States Thoroughbred racing season]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: United States Thoroughbred racing season
Context triple: [American Horse of the Year, geographicFocus, United States Thoroughbred racing season]
  • A. North American Thoroughbred racing industry
    The North American Thoroughbred racing industry is the commercial and sporting ecosystem centered on breeding, training, and racing Thoroughbred horses across the United States and Canada.
  • B. North American harness racing
    North American harness racing is a form of horse racing in which Standardbred horses pull a two-wheeled cart (sulky) at a specific gait, featuring major events and series such as the Trotting Triple Crown.
  • C. United States horse racing tracks
    United States horse racing tracks are specialized sporting venues across the country where Thoroughbred, Standardbred, and Quarter Horse races are held for competition, wagering, and entertainment.
  • D. National Thoroughbred Racing Association
    The National Thoroughbred Racing Association is a U.S.-based organization that serves as the governing and promotional body for Thoroughbred horse racing, overseeing major industry initiatives, awards, and marketing efforts.
  • E. The Jockey Club (US)
    The Jockey Club (US) is the primary registry and regulatory authority for Thoroughbred horse breeding and racing in the United States.
  • 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: United States Thoroughbred racing season
Triple: [American Horse of the Year, geographicFocus, United States Thoroughbred racing season]
Generated description
The United States Thoroughbred racing season is the annual calendar of major flat races and stakes events in American horse racing, culminating in prestigious awards and championships.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: United States Thoroughbred racing season
Target entity description: The United States Thoroughbred racing season is the annual calendar of major flat races and stakes events in American horse racing, culminating in prestigious awards and championships.
  • A. North American Thoroughbred racing industry
    The North American Thoroughbred racing industry is the commercial and sporting ecosystem centered on breeding, training, and racing Thoroughbred horses across the United States and Canada.
  • B. North American harness racing
    North American harness racing is a form of horse racing in which Standardbred horses pull a two-wheeled cart (sulky) at a specific gait, featuring major events and series such as the Trotting Triple Crown.
  • C. United States horse racing tracks
    United States horse racing tracks are specialized sporting venues across the country where Thoroughbred, Standardbred, and Quarter Horse races are held for competition, wagering, and entertainment.
  • D. National Thoroughbred Racing Association
    The National Thoroughbred Racing Association is a U.S.-based organization that serves as the governing and promotional body for Thoroughbred horse racing, overseeing major industry initiatives, awards, and marketing efforts.
  • E. The Jockey Club (US)
    The Jockey Club (US) is the primary registry and regulatory authority for Thoroughbred horse breeding and racing in the United States.
  • 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_69d8b916a2d081909e249e4902f6aad9 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50aa4d3308190883714e1ef6a1d84 completed April 19, 2026, 5:02 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03c4c6094881909add4e2fe99a1bba completed May 13, 2026, 12:24 a.m.
NEDg Description generation batch_6a03c52d0ba48190845d461df02c3aa3 completed May 13, 2026, 12:26 a.m.
NED2 Entity disambiguation (via description) batch_6a03c5dd07488190ae04c6b406ab29c9 completed May 13, 2026, 12:29 a.m.
Created at: April 10, 2026, 10:36 a.m.