Triple

T6642881
Position Surface form Disambiguated ID Type / Status
Subject Lady Constance Keeble E150628 entity
Predicate spouse P13 FINISHED
Object Joseph Keeble
Joseph Keeble is a fictional wealthy, good-natured financier in P. G. Wodehouse’s Blandings Castle stories, known for his indulgent generosity and mild-mannered temperament.
E622335 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: Joseph Keeble | Statement: [Lady Constance Keeble, spouse, Joseph Keeble]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joseph Keeble
Context triple: [Lady Constance Keeble, spouse, Joseph Keeble]
  • A. John Keeble
    John Keeble is an English drummer best known as a founding member of the 1980s new wave band Spandau Ballet.
  • B. Robert Keene
    Robert Keene was the husband of American Abstract Expressionist painter Grace Hartigan.
  • C. Anthony Peckham
    Anthony Peckham is a South African–born screenwriter best known for scripting films such as "Invictus" and "Sherlock Holmes."
  • D. Joseph McHardy
    Joseph McHardy is a musician and choral director known for his work with prominent British church and cathedral choirs.
  • E. Charles Bebb
    Charles Bebb was a prominent early 20th-century American architect based in Seattle, known for helping shape the city's skyline through major commercial and landmark buildings.
  • 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: Joseph Keeble
Triple: [Lady Constance Keeble, spouse, Joseph Keeble]
Generated description
Joseph Keeble is a fictional wealthy, good-natured financier in P. G. Wodehouse’s Blandings Castle stories, known for his indulgent generosity and mild-mannered temperament.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Joseph Keeble
Target entity description: Joseph Keeble is a fictional wealthy, good-natured financier in P. G. Wodehouse’s Blandings Castle stories, known for his indulgent generosity and mild-mannered temperament.
  • A. John Keeble
    John Keeble is an English drummer best known as a founding member of the 1980s new wave band Spandau Ballet.
  • B. Robert Keene
    Robert Keene was the husband of American Abstract Expressionist painter Grace Hartigan.
  • C. Anthony Peckham
    Anthony Peckham is a South African–born screenwriter best known for scripting films such as "Invictus" and "Sherlock Holmes."
  • D. Joseph McHardy
    Joseph McHardy is a musician and choral director known for his work with prominent British church and cathedral choirs.
  • E. Charles Bebb
    Charles Bebb was a prominent early 20th-century American architect based in Seattle, known for helping shape the city's skyline through major commercial and landmark buildings.
  • 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_69c687f1a3048190828b7342f7125d5c completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6aff749d48190bf24d448daf13bc7 completed March 27, 2026, 4:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c723b575a08190a3e0b1f233c36ba0 completed March 28, 2026, 12:41 a.m.
NEDg Description generation batch_69c724a4f64481908676d15a09e9db28 completed March 28, 2026, 12:45 a.m.
NED2 Entity disambiguation (via description) batch_69c725814d188190bd158292b34a553f completed March 28, 2026, 12:49 a.m.
Created at: March 27, 2026, 2 p.m.