Triple

T5271720
Position Surface form Disambiguated ID Type / Status
Subject Paul Haggis E119272 entity
Predicate spouse P13 FINISHED
Object Diana Gettas
Diana Gettas is known as the former wife of Canadian screenwriter and director Paul Haggis.
E514766 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: Diana Gettas | Statement: [Paul Haggis, spouse, Diana Gettas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diana Gettas
Context triple: [Paul Haggis, spouse, Diana Gettas]
  • A. Diana Gould
    Diana Gould was a British ballerina and actress best known for her distinguished dance career and her marriage to renowned violinist Yehudi Menuhin.
  • B. Diana Goodman
    Diana Goodman is the emotionally struggling suburban mother at the center of the rock musical "Next to Normal," whose battle with mental illness drives the show's narrative.
  • C. Kathleen DuRoss
    Kathleen DuRoss was an American former model and socialite best known as the third wife of industrialist Henry Ford II.
  • D. Glena Goranson
    Glena Goranson is the longtime wife of NFL coach Pete Carroll, known for her low public profile despite her husband’s high-profile football career.
  • E. Virginia Weidler
    Virginia Weidler was an American child actress of the 1930s and 1940s, best remembered for her witty supporting roles in classic Hollywood films such as "The Philadelphia Story."
  • 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: Diana Gettas
Triple: [Paul Haggis, spouse, Diana Gettas]
Generated description
Diana Gettas is known as the former wife of Canadian screenwriter and director Paul Haggis.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Diana Gettas
Target entity description: Diana Gettas is known as the former wife of Canadian screenwriter and director Paul Haggis.
  • A. Diana Gould
    Diana Gould was a British ballerina and actress best known for her distinguished dance career and her marriage to renowned violinist Yehudi Menuhin.
  • B. Diana Goodman
    Diana Goodman is the emotionally struggling suburban mother at the center of the rock musical "Next to Normal," whose battle with mental illness drives the show's narrative.
  • C. Kathleen DuRoss
    Kathleen DuRoss was an American former model and socialite best known as the third wife of industrialist Henry Ford II.
  • D. Glena Goranson
    Glena Goranson is the longtime wife of NFL coach Pete Carroll, known for her low public profile despite her husband’s high-profile football career.
  • E. Virginia Weidler
    Virginia Weidler was an American child actress of the 1930s and 1940s, best remembered for her witty supporting roles in classic Hollywood films such as "The Philadelphia Story."
  • 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_69bd446c38e081908cdaf113bdf86790 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7c1fa01081909d589686289b624b completed March 20, 2026, 4:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf290430a08190bf4f00a558d5a1fa completed March 21, 2026, 11:25 p.m.
NEDg Description generation batch_69bf29886f00819096639d721a4a5d80 completed March 21, 2026, 11:28 p.m.
NED2 Entity disambiguation (via description) batch_69bf29e25d80819094f03f02234c357b completed March 21, 2026, 11:29 p.m.
Created at: March 20, 2026, 1:51 p.m.