Triple

T15260469
Position Surface form Disambiguated ID Type / Status
Subject Eclipse E364760 entity
Predicate trainedBy P3665 FINISHED
Object John Oakley
John Oakley is a horse trainer best known for conditioning the racehorse Eclipse, one of the most dominant and influential Thoroughbreds in racing history.
E1226730 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: John Oakley | Statement: [Eclipse, trainedBy, John Oakley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Oakley
Context triple: [Eclipse, trainedBy, John Oakley]
  • A. John Dolman
    John Dolman was an English clergyman and benefactor of the late 16th century best known for establishing Pocklington School in Yorkshire.
  • B. Richard Oakes
    Richard Oakes was a Mohawk Native American activist best known for helping lead the 1969–1971 occupation of Alcatraz Island, a landmark protest in the Red Power movement.
  • C. Ted Oakes
    Ted Oakes is a wildlife television producer and filmmaker known for creating high-profile nature documentaries.
  • D. Jack Holbrook
    Jack Holbrook is a relatively obscure individual known primarily as a namesake associated with the surname Holbrook.
  • E. Michael Holbrook
    Michael Holbrook is a personal name most notably associated with individuals in English-speaking countries, sometimes appearing as a given and family name combination.
  • 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: John Oakley
Triple: [Eclipse, trainedBy, John Oakley]
Generated description
John Oakley is a horse trainer best known for conditioning the racehorse Eclipse, one of the most dominant and influential Thoroughbreds in racing history.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John Oakley
Target entity description: John Oakley is a horse trainer best known for conditioning the racehorse Eclipse, one of the most dominant and influential Thoroughbreds in racing history.
  • A. John Dolman
    John Dolman was an English clergyman and benefactor of the late 16th century best known for establishing Pocklington School in Yorkshire.
  • B. Richard Oakes
    Richard Oakes was a Mohawk Native American activist best known for helping lead the 1969–1971 occupation of Alcatraz Island, a landmark protest in the Red Power movement.
  • C. Ted Oakes
    Ted Oakes is a wildlife television producer and filmmaker known for creating high-profile nature documentaries.
  • D. Jack Holbrook
    Jack Holbrook is a relatively obscure individual known primarily as a namesake associated with the surname Holbrook.
  • E. Michael Holbrook
    Michael Holbrook is a personal name most notably associated with individuals in English-speaking countries, sometimes appearing as a given and family name combination.
  • 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_69d85a0f08408190b3c3259ae35d79d2 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0084e85a08190b8e63598b9f6a535 completed April 15, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_6a008a1d8e088190a2168952ab5dc687 completed May 10, 2026, 1:37 p.m.
NEDg Description generation batch_6a008b1b3bcc81908b1b811ed42205ec completed May 10, 2026, 1:41 p.m.
NED2 Entity disambiguation (via description) batch_6a008b7c29e88190b5a049cb2e541a8f completed May 10, 2026, 1:43 p.m.
Created at: April 10, 2026, 3:14 a.m.