Triple

T9805855
Position Surface form Disambiguated ID Type / Status
Subject Jack Twyman E237950 entity
Predicate spouse P13 FINISHED
Object Caroline Twyman
Caroline Twyman is known as the wife of Hall of Fame NBA player and longtime Cincinnati Royals star Jack Twyman.
E828982 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: Caroline Twyman | Statement: [Jack Twyman, spouse, Caroline Twyman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Caroline Twyman
Context triple: [Jack Twyman, spouse, Caroline Twyman]
  • A. Caroline Fall
    Caroline Fall was a daughter of Albert B. Fall, the U.S. Secretary of the Interior implicated in the Teapot Dome scandal.
  • B. Caroline Burt
    Caroline Burt is the wife of English physicist and science communicator Brian Cox, known primarily for her private life away from the public spotlight.
  • C. Caroline Fentress
    Caroline Fentress is an American schoolteacher best known as the wife of actor Chris O'Donnell.
  • D. Caroline Thompson
    Caroline Thompson is an American screenwriter and director best known for her work on darkly whimsical films such as Edward Scissorhands, The Nightmare Before Christmas, and Corpse Bride.
  • E. Caroline Ford
    Caroline Ford is a British actress best known for her role in the fantasy television series "Carnival Row."
  • 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: Caroline Twyman
Triple: [Jack Twyman, spouse, Caroline Twyman]
Generated description
Caroline Twyman is known as the wife of Hall of Fame NBA player and longtime Cincinnati Royals star Jack Twyman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Caroline Twyman
Target entity description: Caroline Twyman is known as the wife of Hall of Fame NBA player and longtime Cincinnati Royals star Jack Twyman.
  • A. Caroline Fall
    Caroline Fall was a daughter of Albert B. Fall, the U.S. Secretary of the Interior implicated in the Teapot Dome scandal.
  • B. Caroline Burt
    Caroline Burt is the wife of English physicist and science communicator Brian Cox, known primarily for her private life away from the public spotlight.
  • C. Caroline Fentress
    Caroline Fentress is an American schoolteacher best known as the wife of actor Chris O'Donnell.
  • D. Caroline Thompson
    Caroline Thompson is an American screenwriter and director best known for her work on darkly whimsical films such as Edward Scissorhands, The Nightmare Before Christmas, and Corpse Bride.
  • E. Caroline Ford
    Caroline Ford is a British actress best known for her role in the fantasy television series "Carnival Row."
  • 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_69ca84dd4608819097ff4ed00feca280 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdab7b67748190ba16ce868f29d13e completed April 1, 2026, 11:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69d20d1b170881908954233f927457a0 completed April 5, 2026, 7:19 a.m.
NEDg Description generation batch_69d2102beb4481909e88f37384cee4e5 completed April 5, 2026, 7:33 a.m.
NED2 Entity disambiguation (via description) batch_69d210fed02c8190bde2dfa7e81b1ef2 completed April 5, 2026, 7:36 a.m.
Created at: March 30, 2026, 8:29 p.m.