Triple

T4089898
Position Surface form Disambiguated ID Type / Status
Subject Evelyn Waugh E87679 entity
Predicate spouse P13 FINISHED
Object Laura Herbert E150430 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: Laura Herbert | Statement: [Evelyn Waugh, spouse, Laura Herbert]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laura Herbert
Context triple: [Evelyn Waugh, spouse, Laura Herbert]
  • A. Laura Herbert chosen
    Laura Herbert was the second wife of British novelist Evelyn Waugh, with whom he had seven children and maintained a prominent place in his personal and literary life.
  • B. Jayma Mays
    Jayma Mays is an American actress best known for her roles in the television series "Glee" and films such as "Red Eye" and "Paul Blart: Mall Cop."
  • C. Hilary Cummins
    Hilary Cummins is the obsessive, piano-playing scholar whose encounter with a severed, seemingly autonomous hand drives the supernatural horror in the film "The Beast with Five Fingers."
  • D. Jennifer Williams
    Jennifer Williams is known as the daughter of acclaimed American composer and conductor John Williams.
  • E. Lindsey Weber
    Lindsey Weber is a film and television producer known for her work on major genre projects including the science-fiction blockbuster "Star Trek Beyond."
  • 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_69aed94425148190be337845d56fac22 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefcab0a1c8190a1b0ca48ebc95b31 completed March 9, 2026, 5 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5769e8b188190a6356c325d0551ea completed March 14, 2026, 2:54 p.m.
Created at: March 9, 2026, 3:39 p.m.