Triple

T13348762
Position Surface form Disambiguated ID Type / Status
Subject The Undertaker E318019 entity
Predicate trainedBy P3665 FINISHED
Object Buzz Sawyer
Buzz Sawyer was an American professional wrestler known for his intense, hard-hitting style and influential role as a trainer in the wrestling industry.
E1035132 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: Buzz Sawyer | Statement: [The Undertaker, trainedBy, Buzz Sawyer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Buzz Sawyer
Context triple: [The Undertaker, trainedBy, Buzz Sawyer]
  • A. Sid Sawyer
    Sid Sawyer is Tom Sawyer’s well-behaved but tattling half-brother in Mark Twain’s classic novel "The Adventures of Tom Sawyer."
  • B. James Scudder
    James Scudder is an American evangelical pastor and broadcaster best known for founding and leading the Quentin Road Baptist Church and its associated media ministries.
  • C. Max Drummey
    Max Drummey is an American musician best known as the guitarist and co-founder of the indie pop band Chester French.
  • D. Tom Rowe
    Tom Rowe is a writer best known for contributing to the story of Disney’s animated film "The Aristocats."
  • E. Luke Burbank
    Luke Burbank is an American radio host and podcaster best known for his work on public radio programs and his humorous commentary on current events.
  • 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: Buzz Sawyer
Triple: [The Undertaker, trainedBy, Buzz Sawyer]
Generated description
Buzz Sawyer was an American professional wrestler known for his intense, hard-hitting style and influential role as a trainer in the wrestling industry.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Buzz Sawyer
Target entity description: Buzz Sawyer was an American professional wrestler known for his intense, hard-hitting style and influential role as a trainer in the wrestling industry.
  • A. Sid Sawyer
    Sid Sawyer is Tom Sawyer’s well-behaved but tattling half-brother in Mark Twain’s classic novel "The Adventures of Tom Sawyer."
  • B. James Scudder
    James Scudder is an American evangelical pastor and broadcaster best known for founding and leading the Quentin Road Baptist Church and its associated media ministries.
  • C. Max Drummey
    Max Drummey is an American musician best known as the guitarist and co-founder of the indie pop band Chester French.
  • D. Tom Rowe
    Tom Rowe is a writer best known for contributing to the story of Disney’s animated film "The Aristocats."
  • E. Luke Burbank
    Luke Burbank is an American radio host and podcaster best known for his work on public radio programs and his humorous commentary on current events.
  • 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_69d806b5a3c08190b42c267fb092f98a completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d99e8b28e48190a23194e03a74b41b completed April 11, 2026, 1:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69f71f45c9788190b60095c0d6e2f763 completed May 3, 2026, 10:11 a.m.
NEDg Description generation batch_69f720bb48f081908d67d330dcfc2953 completed May 3, 2026, 10:17 a.m.
NED2 Entity disambiguation (via description) batch_69f721baaf34819081113c586fae013f completed May 3, 2026, 10:21 a.m.
Created at: April 9, 2026, 9:31 p.m.