Triple

T18044825
Position Surface form Disambiguated ID Type / Status
Subject Affirmed E431743 entity
Predicate notableOffspring P4268 FINISHED
Object Peteski
Peteski is a Thoroughbred racehorse best known as a Canadian champion and Queen’s Plate winner, and a notable son of the U.S. Triple Crown winner Affirmed.
E1302254 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: Peteski | Statement: [Affirmed, notableOffspring, Peteski]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peteski
Context triple: [Affirmed, notableOffspring, Peteski]
  • A. The Pete
    The Pete is a multi-purpose indoor arena at the University of Pittsburgh known primarily as the home venue for the Pittsburgh Panthers basketball teams.
  • B. Pete
    Pete is a supporting character in the comedy film "Knocked Up," portrayed as the somewhat immature yet well-meaning husband of Debbie and friend of the protagonist.
  • C. Pete
    Pete is a common masculine given name, typically used as a familiar or informal form of the name Peter.
  • D. Pete
    Pete is a classic Disney cartoon villain, best known as Mickey Mouse’s burly, antagonistic foe in the Mickey Mouse franchise.
  • E. Pete
    Pete is a fictional character known as the son of Uncle Tom in Harriet Beecher Stowe’s anti-slavery novel "Uncle Tom’s Cabin."
  • 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: Peteski
Triple: [Affirmed, notableOffspring, Peteski]
Generated description
Peteski is a Thoroughbred racehorse best known as a Canadian champion and Queen’s Plate winner, and a notable son of the U.S. Triple Crown winner Affirmed.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Peteski
Target entity description: Peteski is a Thoroughbred racehorse best known as a Canadian champion and Queen’s Plate winner, and a notable son of the U.S. Triple Crown winner Affirmed.
  • A. The Pete
    The Pete is a multi-purpose indoor arena at the University of Pittsburgh known primarily as the home venue for the Pittsburgh Panthers basketball teams.
  • B. Pete
    Pete is a common masculine given name, typically used as a familiar or informal form of the name Peter.
  • C. Pete
    Pete is a classic Disney cartoon villain, best known as Mickey Mouse’s burly, antagonistic foe in the Mickey Mouse franchise.
  • D. Pete
    Pete is a fictional character known as the son of Uncle Tom in Harriet Beecher Stowe’s anti-slavery novel "Uncle Tom’s Cabin."
  • E. Pete
    Pete is the nickname of Frank K. Everest Jr., a renowned United States Air Force test pilot and brigadier general known for his high-speed flight records.
  • 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_69d8b906482481908183315b9ecf9994 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4bff13f488190993445769551c9c2 completed April 19, 2026, 11:43 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0349bb99508190ba6b1f8e4ac2b599 completed May 12, 2026, 3:39 p.m.
NEDg Description generation batch_6a034b4fd4fc8190bd75aa51a8f3d2d4 completed May 12, 2026, 3:46 p.m.
NED2 Entity disambiguation (via description) batch_6a034bc081d08190aa29065fdaecc5b2 completed May 12, 2026, 3:48 p.m.
Created at: April 10, 2026, 10:25 a.m.