Triple

T412289
Position Surface form Disambiguated ID Type / Status
Subject Bob Woodward E9514 entity
Predicate previousSpouse P493 FINISHED
Object Frances Kuper
Frances Kuper is known as a former spouse of investigative journalist and author Bob Woodward.
E89689 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: Frances Kuper | Statement: [Bob Woodward, previousSpouse, Frances Kuper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frances Kuper
Context triple: [Bob Woodward, previousSpouse, Frances Kuper]
  • A. Franziska Boas
    Franziska Boas was an American modern dancer, percussionist, and dance educator known for integrating anthropology, improvisation, and social activism into her work.
  • B. Muriel Whiting
    Muriel Whiting was the wife of British Royal Air Force commander Hugh Dowding, 1st Baron Dowding, noted for his leadership during the Battle of Britain.
  • C. Harriet Eckersall
    Harriet Eckersall was the wife of the influential British economist and demographer Thomas Robert Malthus.
  • D. Ruth Josephine Googins
    Ruth Josephine Googins was the first wife of Elliott Roosevelt, son of U.S. President Franklin D. Roosevelt and Eleanor Roosevelt.
  • E. Katharine Towne
    Katharine Towne is an American actress known for her roles in films such as "She's All That," "Mulholland Drive," and "What Lies Beneath."
  • 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: Frances Kuper
Triple: [Bob Woodward, previousSpouse, Frances Kuper]
Generated description
Frances Kuper is known as a former spouse of investigative journalist and author Bob Woodward.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Frances Kuper
Target entity description: Frances Kuper is known as a former spouse of investigative journalist and author Bob Woodward.
  • A. Franziska Boas
    Franziska Boas was an American modern dancer, percussionist, and dance educator known for integrating anthropology, improvisation, and social activism into her work.
  • B. Muriel Whiting
    Muriel Whiting was the wife of British Royal Air Force commander Hugh Dowding, 1st Baron Dowding, noted for his leadership during the Battle of Britain.
  • C. Harriet Eckersall
    Harriet Eckersall was the wife of the influential British economist and demographer Thomas Robert Malthus.
  • D. Ruth Josephine Googins
    Ruth Josephine Googins was the first wife of Elliott Roosevelt, son of U.S. President Franklin D. Roosevelt and Eleanor Roosevelt.
  • E. Katharine Towne
    Katharine Towne is an American actress known for her roles in films such as "She's All That," "Mulholland Drive," and "What Lies Beneath."
  • 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_69a2e80111fc8190961d5b7c6154123f completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2ee2d6fe481908ff70ab7d043bb3e completed Feb. 28, 2026, 1:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69a65e2e20c08190af76454812a0c88b completed March 3, 2026, 4:06 a.m.
NEDg Description generation batch_69a65ef36bac8190806ab440c3bdd6fa completed March 3, 2026, 4:09 a.m.
NED2 Entity disambiguation (via description) batch_69a65f5c0ec88190888d4e8ca3fc04fc completed March 3, 2026, 4:11 a.m.
Created at: Feb. 28, 2026, 1:09 p.m.