Triple

T15555576
Position Surface form Disambiguated ID Type / Status
Subject Abe Vigoda E370857 entity
Predicate spouse P13 FINISHED
Object Beatrice Schy
Beatrice Schy was the longtime wife of American character actor Abe Vigoda.
E1164034 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 Schy | Statement: [Abe Vigoda, spouse, Beatrice Schy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Beatrice Schy
Context triple: [Abe Vigoda, spouse, Beatrice Schy]
  • A. Beatrice Sisul
    Beatrice Sisul is a film editor known for her work on the thriller "Message from the King."
  • B. Beatrice Taylor
    Beatrice Taylor is the beloved, nurturing aunt character from "The Andy Griffith Show," best known for her role as Aunt Bee in the fictional town of Mayberry.
  • C. Beatrice Miller
    Beatrice Miller is an American singer and actress who gained prominence as a contestant on the U.S. version of The X Factor.
  • D. Beatrice Pearson
    Beatrice Pearson was an American film actress best known for her leading role in the 1948 film noir "Force of Evil."
  • E. Beatrice Hennessy
    Beatrice Hennessy is the child of Tamar Teresa Day Hennessy.
  • 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 Schy
Triple: [Abe Vigoda, spouse, Beatrice Schy]
Generated description
Beatrice Schy was the longtime wife of American character actor Abe Vigoda.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Beatrice Schy
Target entity description: Beatrice Schy was the longtime wife of American character actor Abe Vigoda.
  • A. Beatrice Sisul
    Beatrice Sisul is a film editor known for her work on the thriller "Message from the King."
  • B. Beatrice Taylor
    Beatrice Taylor is the beloved, nurturing aunt character from "The Andy Griffith Show," best known for her role as Aunt Bee in the fictional town of Mayberry.
  • C. Beatrice Miller
    Beatrice Miller is an American singer and actress who gained prominence as a contestant on the U.S. version of The X Factor.
  • D. Beatrice Pearson
    Beatrice Pearson was an American film actress best known for her leading role in the 1948 film noir "Force of Evil."
  • E. Beatrice Hennessy
    Beatrice Hennessy is the child of Tamar Teresa Day Hennessy.
  • 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_69d85cc6cf40819091f4a5facee1ebe6 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04a97dbfc8190a98cbbac5e71ba88 completed April 16, 2026, 2:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff456427988190bddea01f5cb159d9 completed May 9, 2026, 2:32 p.m.
NEDg Description generation batch_69ff470492f48190852ede832157ed10 completed May 9, 2026, 2:39 p.m.
NED2 Entity disambiguation (via description) batch_69ff47e5647c81909b785a1212c4bc50 completed May 9, 2026, 2:42 p.m.
Created at: April 10, 2026, 4:09 a.m.