Triple

T7242148
Position Surface form Disambiguated ID Type / Status
Subject Kershaw E156381 entity
Predicate hasNotableBearer P458 FINISHED
Object Steve Kershaw
Steve Kershaw is a British classicist, author, and lecturer known for his works on ancient Greek and Roman history and mythology.
E659258 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: Steve Kershaw | Statement: [Kershaw, hasNotableBearer, Steve Kershaw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steve Kershaw
Context triple: [Kershaw, hasNotableBearer, Steve Kershaw]
  • A. Peter Kershaw
    Peter Kershaw is a notable individual distinguished enough to be recognized as a prominent bearer of the surname Kershaw.
  • B. Doug Kershaw
    Doug Kershaw is an American Cajun fiddler and singer known for his energetic performances and for popularizing Cajun music to mainstream audiences.
  • C. Michael Jessop
    Michael Jessop is a member of the Derby Philosophical Society, a learned society dedicated to scientific and intellectual inquiry in Derby, England.
  • D. Graham Walters
    Graham Walters is a film producer best known for his work on the acclaimed Pixar animated feature "Finding Nemo."
  • E. Bob Shawkey
    Bob Shawkey was an American Major League Baseball pitcher and later manager, best known for his successful career with the New York Yankees in the 1910s and 1920s.
  • 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: Steve Kershaw
Triple: [Kershaw, hasNotableBearer, Steve Kershaw]
Generated description
Steve Kershaw is a British classicist, author, and lecturer known for his works on ancient Greek and Roman history and mythology.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Steve Kershaw
Target entity description: Steve Kershaw is a British classicist, author, and lecturer known for his works on ancient Greek and Roman history and mythology.
  • A. Peter Kershaw
    Peter Kershaw is a notable individual distinguished enough to be recognized as a prominent bearer of the surname Kershaw.
  • B. Doug Kershaw
    Doug Kershaw is an American Cajun fiddler and singer known for his energetic performances and for popularizing Cajun music to mainstream audiences.
  • C. Michael Jessop
    Michael Jessop is a member of the Derby Philosophical Society, a learned society dedicated to scientific and intellectual inquiry in Derby, England.
  • D. Graham Walters
    Graham Walters is a film producer best known for his work on the acclaimed Pixar animated feature "Finding Nemo."
  • E. Bob Shawkey
    Bob Shawkey was an American Major League Baseball pitcher and later manager, best known for his successful career with the New York Yankees in the 1910s and 1920s.
  • 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_69c68827b5e481908dc05e145b2c92d4 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ea552a688190a00f5d0ad982f787 completed March 27, 2026, 8:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7fa6ad54081908a0be2d1f7d6505e completed March 28, 2026, 3:57 p.m.
NEDg Description generation batch_69c7fcc2cc4c8190871287fdf4338ebd completed March 28, 2026, 4:07 p.m.
NED2 Entity disambiguation (via description) batch_69c7fd12d1f08190b0ae80fdc7e17cc5 completed March 28, 2026, 4:08 p.m.
Created at: March 27, 2026, 2:55 p.m.