Triple

T23232675
Position Surface form Disambiguated ID Type / Status
Subject Dolores Hart E581203 entity
Predicate name P16 FINISHED
Object Dolores Hart NE NERFINISHED

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: Dolores Hart | Statement: [Dolores Hart, name, Dolores Hart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dolores Hart
Context triple: [Dolores Hart, name, Dolores Hart]
  • A. Dolores Hart chosen
    Dolores Hart is an American former film and television actress best known for her roles opposite Elvis Presley in the late 1950s before leaving Hollywood to become a Roman Catholic nun.
  • B. April Ryan
    April Ryan is the central heroine of the adventure game "The Longest Journey," known for her ability to shift between parallel worlds of science and magic.
  • C. Lala Ward
    Lala Ward is a British actress best known for playing the Time Lady Romana in the long-running science fiction television series Doctor Who.
  • D. Barbara Kane
    Barbara Kane is known primarily as the wife of Arthur Kane, the bassist and founding member of the influential punk rock band the New York Dolls.
  • E. Joan Greenwood
    Joan Greenwood was a distinctive English actress renowned for her husky voice and roles in classic British films such as "Kind Hearts and Coronets" and "The Man in the White Suit."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e246043c48819089bae72c9a9c306c completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f192e70b2c8190abede6e3cd9344f7 completed April 29, 2026, 5:11 a.m.
Created at: April 17, 2026, 4:09 p.m.