Triple

T17865919
Position Surface form Disambiguated ID Type / Status
Subject Willard Mack E446700 entity
Predicate spouse P13 FINISHED
Object Beatrice Banyard
Beatrice Banyard was an actress and the wife of Canadian-American playwright, actor, and director Willard Mack.
E1291705 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: Beatrice Banyard | Statement: [Willard Mack, spouse, Beatrice Banyard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Beatrice Banyard
Context triple: [Willard Mack, spouse, Beatrice Banyard]
  • A. Beatrice Hennessy
    Beatrice Hennessy is the child of Tamar Teresa Day Hennessy.
  • B. Beatrice Durham
    Beatrice Durham was the wife of pioneering British geneticist William Bateson and a supportive figure in his personal and scientific life.
  • C. Beatrice Schy
    Beatrice Schy was the longtime wife of American character actor Abe Vigoda.
  • D. Beatrice Dawson
    Beatrice Dawson was a British costume designer known for her work on mid-20th-century films, earning multiple Academy Award nominations for her period and character costumes.
  • E. Beatrice Henderson
    Beatrice Henderson is the central character in the 1996 film "Mother," a middle-aged writer who moves back in with his sharp-tongued, emotionally complex mother to work through their strained relationship.
  • 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: Beatrice Banyard
Triple: [Willard Mack, spouse, Beatrice Banyard]
Generated description
Beatrice Banyard was an actress and the wife of Canadian-American playwright, actor, and director Willard Mack.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Beatrice Banyard
Target entity description: Beatrice Banyard was an actress and the wife of Canadian-American playwright, actor, and director Willard Mack.
  • A. Beatrice Hennessy
    Beatrice Hennessy is the child of Tamar Teresa Day Hennessy.
  • B. Beatrice Durham
    Beatrice Durham was the wife of pioneering British geneticist William Bateson and a supportive figure in his personal and scientific life.
  • C. Beatrice Schy
    Beatrice Schy was the longtime wife of American character actor Abe Vigoda.
  • D. Beatrice Dawson
    Beatrice Dawson was a British costume designer known for her work on mid-20th-century films, earning multiple Academy Award nominations for her period and character costumes.
  • E. Beatrice Henderson
    Beatrice Henderson is the central character in the 1996 film "Mother," a middle-aged writer who moves back in with his sharp-tongued, emotionally complex mother to work through their strained relationship.
  • 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_69d8b9f4c22c819093c2680434472894 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49793a2588190bb341ac606d767fe completed April 19, 2026, 8:51 a.m.
NED1 Entity disambiguation (via context triple) batch_6a030c69cd608190b25002100fc0f9e3 completed May 12, 2026, 11:18 a.m.
NEDg Description generation batch_6a030ce6e0248190854acf6ad772cb08 completed May 12, 2026, 11:20 a.m.
NED2 Entity disambiguation (via description) batch_6a030d4d117c8190a115b86df7990087 completed May 12, 2026, 11:21 a.m.
Created at: April 10, 2026, 10:17 a.m.