Triple

T9245062
Position Surface form Disambiguated ID Type / Status
Subject William Hurt E222168 entity
Predicate spouse P13 FINISHED
Object Heidi Henderson
Heidi Henderson is known as the former spouse of the late American actor William Hurt.
 E851230 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: Heidi Henderson | Statement: [William Hurt, spouse, Heidi Henderson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Heidi Henderson
Context triple: [William Hurt, spouse, Heidi Henderson]
  • A. Heather Burns
    Heather Burns is an American actress best known for her comedic supporting roles in films such as "Miss Congeniality" and "You've Got Mail."
  • B. Kristina Hetherington
    Kristina Hetherington is a film editor known for her work on the psychological period drama "The Wonder."
  • C. Laura Henderson
    Laura Henderson is a wealthy, eccentric British widow best known as the real-life owner of London’s Windmill Theatre, whose story inspired the film "Mrs Henderson Presents."
  • D. Heather Persons
    Heather Persons is a film editor best known for her work on the independent comedy-drama "Sunshine Cleaning."
  • E. Meg Haston
    Meg Haston is an American author best known for her middle-grade and young adult novels, including the book that inspired the Nickelodeon television series "How to Rock."
  • 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: Heidi Henderson
Triple: [William Hurt, spouse, Heidi Henderson]
Generated description
Heidi Henderson is known as the former spouse of the late American actor William Hurt.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Heidi Henderson
Target entity description: Heidi Henderson is known as the former spouse of the late American actor William Hurt.
  • A. Heather Burns
    Heather Burns is an American actress best known for her comedic supporting roles in films such as "Miss Congeniality" and "You've Got Mail."
  • B. Kristina Hetherington
    Kristina Hetherington is a film editor known for her work on the psychological period drama "The Wonder."
  • C. Laura Henderson
    Laura Henderson is a wealthy, eccentric British widow best known as the real-life owner of London’s Windmill Theatre, whose story inspired the film "Mrs Henderson Presents."
  • D. Heather Persons
    Heather Persons is a film editor best known for her work on the independent comedy-drama "Sunshine Cleaning."
  • E. Meg Haston
    Meg Haston is an American author best known for her middle-grade and young adult novels, including the book that inspired the Nickelodeon television series "How to Rock."
  • 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_69ca83ee26cc81909ac624e190597d6d completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cd03efaa748190973916bd790f6e3a completed April 1, 2026, 11:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f67c3a0881909f24d85d74e4c061 completed April 9, 2026, 12:44 a.m.
NEDg Description generation batch_69d6fa2bb2ec8190aa099988a6c225eb completed April 9, 2026, 1 a.m.
NED2 Entity disambiguation (via description) batch_69d6fd10dbc08190a297073e1b737566 completed April 9, 2026, 1:12 a.m.
Created at: March 30, 2026, 7:30 p.m.