Triple

T12326985
Position Surface form Disambiguated ID Type / Status
Subject John McCain E293854 entity
Predicate spouse P13 FINISHED
Object Carol Shepp E325458 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: Carol Shepp | Statement: [John McCain, spouse, Carol Shepp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carol Shepp
Context triple: [John McCain, spouse, Carol Shepp]
  • A. Carol Shepp chosen
    Carol Shepp is an American former model and teacher best known as the first wife of the late U.S. Senator and 2008 Republican presidential nominee John McCain.
  • B. Phyllis Ralph
    Phyllis Ralph was the wife of English stage and film actor Lionel Atwill, known for his prominent roles in early 20th-century horror and mystery films.
  • C. Myrna Fahey
    Myrna Fahey was an American actress known for her film and television roles in the 1950s and 1960s, often appearing in comedies and dramas.
  • D. Eileen Heckart
    Eileen Heckart was an American character actress known for her versatile work on stage, film, and television, including an Academy Award–winning performance in "Butterflies Are Free."
  • E. Joyce Randolph
    Joyce Randolph is an American actress best known for playing Trixie Norton on the classic 1950s television sitcom "The Honeymooners."
  • 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_69d6ab6ae0dc8190b1522a9c1c55c114 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93f4f90a881908c5060dd197744d1 completed April 10, 2026, 6:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f71f05b3e08190be0d4e0ad2bfb2d1 completed May 3, 2026, 10:10 a.m.
Created at: April 8, 2026, 9:53 p.m.