Triple

T6043571
Position Surface form Disambiguated ID Type / Status
Subject John Astin E134608 entity
Predicate spouse P13 FINISHED
Object Suzanne Hahn
Suzanne Hahn is known as the first wife of American actor John Astin, with whom she was married in the mid-20th century.
 E583707 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: Suzanne Hahn | Statement: [John Astin, spouse, Suzanne Hahn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Suzanne Hahn
Context triple: [John Astin, spouse, Suzanne Hahn]
  • A. Suzanne Zimmer
    Suzanne Zimmer is the wife of renowned film composer Hans Zimmer and the mother of several of his children.
  • B. Carol Hagen
    Carol Hagen is an American real estate agent best known as the wife of NBC Nightly News anchor Lester Holt.
  • C. Suzanne Perrin
    Suzanne Perrin was the second wife of Franklin D. Roosevelt Jr., a lawyer and politician and son of U.S. President Franklin D. Roosevelt.
  • D. Suzanne Goldberg
    Suzanne Goldberg is a prominent civil rights lawyer and legal scholar known for her work on free speech and equality issues in the United States.
  • E. Suzanne Goldberg
    Suzanne Goldberg is known as the wife of prominent 1960s Free Speech Movement leader Mario Savio.
  • 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: Suzanne Hahn
Triple: [John Astin, spouse, Suzanne Hahn]
Generated description
Suzanne Hahn is known as the first wife of American actor John Astin, with whom she was married in the mid-20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Suzanne Hahn
Target entity description: Suzanne Hahn is known as the first wife of American actor John Astin, with whom she was married in the mid-20th century.
  • A. Suzanne Zimmer
    Suzanne Zimmer is the wife of renowned film composer Hans Zimmer and the mother of several of his children.
  • B. Carol Hagen
    Carol Hagen is an American real estate agent best known as the wife of NBC Nightly News anchor Lester Holt.
  • C. Suzanne Perrin
    Suzanne Perrin was the second wife of Franklin D. Roosevelt Jr., a lawyer and politician and son of U.S. President Franklin D. Roosevelt.
  • D. Suzanne Goldberg
    Suzanne Goldberg is a prominent civil rights lawyer and legal scholar known for her work on free speech and equality issues in the United States.
  • E. Suzanne Goldberg
    Suzanne Goldberg is known as the wife of prominent 1960s Free Speech Movement leader Mario Savio.
  • 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_69c00876a69881908088a2626d3b2666 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c056e2b1148190908c4dc43abee266 completed March 22, 2026, 8:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69c5e3b108c48190a11ad1a9440fcb12 completed March 27, 2026, 1:56 a.m.
NEDg Description generation batch_69c5ed7144d88190948d8b74c4c09edc completed March 27, 2026, 2:37 a.m.
NED2 Entity disambiguation (via description) batch_69c5ede69fa08190a54dccd00325fb15 completed March 27, 2026, 2:39 a.m.
Created at: March 22, 2026, 4:08 p.m.