Triple

T16468232
Position Surface form Disambiguated ID Type / Status
Subject Phyllis Blankenship E399989 entity
Predicate name P16 FINISHED
Object Phyllis Blankenship E399989 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 Blankenship | Statement: [Phyllis Blankenship, name, Phyllis Blankenship]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Phyllis Blankenship
Context triple: [Phyllis Blankenship, name, Phyllis Blankenship]
  • A. Phyllis Blankenship chosen
    Phyllis Blankenship is known as the former wife of French-American businessman Gérard Louis-Dreyfus and the mother of actress Julia Louis-Dreyfus.
  • B. Phyllis Moore
    Phyllis Moore is known as the first wife of acclaimed British comic book writer Alan Moore.
  • 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. Shirley Yarbrough
    Shirley Yarbrough was the wife of prominent civil rights leader and presidential adviser Vernon E. Jordan Jr.
  • E. Yvonne Cagle
    Yvonne Cagle is an American physician, retired U.S. Air Force Colonel, and NASA astronaut selected in the 1996 astronaut class.
  • 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_69d87f2dac988190b74d6e185fa88ba4 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32dce342081909cad56dc92de13a2 completed April 18, 2026, 7:07 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00581a11e881908681f68c26ee6a05 completed May 10, 2026, 10:04 a.m.
Created at: April 10, 2026, 5:11 a.m.