Triple

T10150990
Position Surface form Disambiguated ID Type / Status
Subject Archibald Cox E232637 entity
Predicate spouse P13 FINISHED
Object Phyllis Ames E232637 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: Phyllis Ames | Statement: [Archibald Cox, spouse, Phyllis Ames]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Phyllis Ames
Context triple: [Archibald Cox, spouse, Phyllis Ames]
  • A. Phyllis Ames chosen
    Phyllis Ames was the wife of Archibald Cox, the prominent American lawyer and Watergate special prosecutor.
  • B. Phyllis Ferguson
    Phyllis Ferguson is known as the spouse of Canadian filmmaker and IMAX co-inventor Graeme Ferguson.
  • C. Phyllis Allen
    Phyllis Allen was an American silent film actress and comedian known for her frequent appearances in early 20th-century slapstick comedies, often alongside stars like Charlie Chaplin.
  • D. Persis Lapham
    Persis Lapham is a central figure in William Dean Howells’s realist novel "The Rise of Silas Lapham," depicted as the morally grounded wife who provides emotional and ethical balance to her ambitious husband.
  • E. Phyllis Newman
    Phyllis Newman was an American actress and singer known for her work on Broadway and television, as well as for her advocacy on behalf of women’s health and entertainment industry professionals.
  • 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_69ca84885e48819088a31b127cf44904 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cdec0584a48190b65daa8370555c27 completed April 2, 2026, 4:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69e5561714a081909cbf1cc7d5d0ac0a completed April 19, 2026, 10:24 p.m.
Created at: March 30, 2026, 9:08 p.m.