Triple

T2737986
Position Surface form Disambiguated ID Type / Status
Subject Katharine Towne E60675 entity
Predicate name P16 FINISHED
Object Katharine Towne E60675 NE FINISHED

How this triple was built (2 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: Katharine Towne | Statement: [Katharine Towne, name, Katharine Towne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Katharine Towne
Context triple: [Katharine Towne, name, Katharine Towne]
  • A. Katharine Towne chosen
    Katharine Towne is an American actress known for her roles in films such as "She's All That," "Mulholland Drive," and "What Lies Beneath."
  • B. Katharine Pember
    Katharine Pember was a British mathematician known for her work in analysis and as the wife of physicist and geneticist Charles Galton Darwin.
  • C. Katherine Emmet
    Katherine Emmet was an American stage and silent film actress active in the early 20th century.
  • D. Elizabeth Wendell
    Elizabeth Wendell was a colonial-era New England woman best known as the mother of Dorothy Quincy, who became the wife of American Founding Father John Hancock.
  • E. Ernestine Bradley
    Ernestine Bradley is a German-American scholar and professor emerita of German and comparative literature, known for her academic work and public engagement in the United States.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ab4b77febc819095603eb012cd141b completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdb147a588190829b74fe05b3a114 completed March 7, 2026, 8 a.m.
NED1 Entity disambiguation (via context triple) batch_69b5281079fc8190a69ae43b14407736 completed March 14, 2026, 9:19 a.m.
Created at: March 6, 2026, 9:56 p.m.