Triple

T2188857
Position Surface form Disambiguated ID Type / Status
Subject John Grisham E49813 entity
Predicate hasChild P369 FINISHED
Object Ty Grisham
Ty Grisham is a child of bestselling American legal-thriller author John Grisham.
E245163 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: Ty Grisham | Statement: [John Grisham, hasChild, Ty Grisham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ty Grisham
Context triple: [John Grisham, hasChild, Ty Grisham]
  • A. John Grisham
    John Grisham is a bestselling American author renowned for his legal thrillers, many of which have been adapted into successful films.
  • B. David Baldacci
    David Baldacci is a bestselling American novelist known for his fast-paced legal and political thrillers, including "Absolute Power" and the "King & Maxwell" series.
  • C. Winston Groom
    Winston Groom was an American novelist and non-fiction writer best known as the author of the novel "Forrest Gump," which inspired the acclaimed film adaptation.
  • D. Tom Wolfe
    Tom Wolfe was an American author and journalist renowned for pioneering New Journalism and writing influential works such as "The Electric Kool-Aid Acid Test" and "The Bonfire of the Vanities."
  • E. Robert Ludlum
    Robert Ludlum was an American author best known for his fast-paced espionage and thriller novels, including the Jason Bourne series.
  • 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: Ty Grisham
Triple: [John Grisham, hasChild, Ty Grisham]
Generated description
Ty Grisham is a child of bestselling American legal-thriller author John Grisham.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ty Grisham
Target entity description: Ty Grisham is a child of bestselling American legal-thriller author John Grisham.
  • A. John Grisham
    John Grisham is a bestselling American author renowned for his legal thrillers, many of which have been adapted into successful films.
  • B. David Baldacci
    David Baldacci is a bestselling American novelist known for his fast-paced legal and political thrillers, including "Absolute Power" and the "King & Maxwell" series.
  • C. Winston Groom
    Winston Groom was an American novelist and non-fiction writer best known as the author of the novel "Forrest Gump," which inspired the acclaimed film adaptation.
  • D. Tom Wolfe
    Tom Wolfe was an American author and journalist renowned for pioneering New Journalism and writing influential works such as "The Electric Kool-Aid Acid Test" and "The Bonfire of the Vanities."
  • E. Robert Ludlum
    Robert Ludlum was an American author best known for his fast-paced espionage and thriller novels, including the Jason Bourne series.
  • 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_69a88aaba3c48190b351cab9b26989ff completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abbf373c608190b7716c137b3e9fe9 completed March 7, 2026, 6:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae65427de48190be3dbc9c0a888332 completed March 9, 2026, 6:14 a.m.
NEDg Description generation batch_69ae6656f7788190818179d923b11bba completed March 9, 2026, 6:19 a.m.
NED2 Entity disambiguation (via description) batch_69ae66cc3ac0819096e3f246b10e7761 completed March 9, 2026, 6:21 a.m.
Created at: March 4, 2026, 7:46 p.m.