Triple

T17933435
Position Surface form Disambiguated ID Type / Status
Subject Haydock Sprint Cup E448390 entity
Predicate notableWinner P2766 FINISHED
Object Averti
Averti was a British Thoroughbred sprinter best known for his Group 1-winning exploits on the flat in the 1990s.
E1296456 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: Averti | Statement: [Haydock Sprint Cup, notableWinner, Averti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Averti
Context triple: [Haydock Sprint Cup, notableWinner, Averti]
  • A. Avin
    Avin is a village in the municipality of Hannut in the province of Liège, Belgium.
  • B. Sauviat
    Sauviat is a commune in central France, located within the Puy-de-Dôme department in the Auvergne region.
  • C. Anzotica
    Anzotica is an Illyrian love and fertility goddess often associated with beauty and sensuality.
  • D. Ravet
    Ravet is a rapidly developing residential suburb in the Pimpri-Chinchwad area of Pune, Maharashtra, known for its proximity to major IT hubs and growing urban infrastructure.
  • E. The Ave
    The Ave is the popular nickname for University Way NE, the central commercial and social hub of Seattle’s University District near the University of Washington.
  • 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: Averti
Triple: [Haydock Sprint Cup, notableWinner, Averti]
Generated description
Averti was a British Thoroughbred sprinter best known for his Group 1-winning exploits on the flat in the 1990s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Averti
Target entity description: Averti was a British Thoroughbred sprinter best known for his Group 1-winning exploits on the flat in the 1990s.
  • A. Avin
    Avin is a village in the municipality of Hannut in the province of Liège, Belgium.
  • B. Sauviat
    Sauviat is a commune in central France, located within the Puy-de-Dôme department in the Auvergne region.
  • C. Anzotica
    Anzotica is an Illyrian love and fertility goddess often associated with beauty and sensuality.
  • D. Ravet
    Ravet is a rapidly developing residential suburb in the Pimpri-Chinchwad area of Pune, Maharashtra, known for its proximity to major IT hubs and growing urban infrastructure.
  • E. The Ave
    The Ave is the popular nickname for University Way NE, the central commercial and social hub of Seattle’s University District near the University of Washington.
  • 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_69d8b9f79d14819095540856928f0e25 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4a55381708190b5dfce6a81bb20d8 completed April 19, 2026, 9:50 a.m.
NED1 Entity disambiguation (via context triple) batch_6a03213a24b48190aad2297210e86d78 completed May 12, 2026, 12:46 p.m.
NEDg Description generation batch_6a0322181a5c8190b34ea80445fc5596 completed May 12, 2026, 12:50 p.m.
NED2 Entity disambiguation (via description) batch_6a0322a4c9448190823e9fdc03ea9f90 completed May 12, 2026, 12:52 p.m.
Created at: April 10, 2026, 10:21 a.m.