Triple

T10540562
Position Surface form Disambiguated ID Type / Status
Subject Cliff Robertson E248682 entity
Predicate spouse P13 FINISHED
Object Cynthia Stone E306644 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: Cynthia Stone | Statement: [Cliff Robertson, spouse, Cynthia Stone]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cynthia Stone
Context triple: [Cliff Robertson, spouse, Cynthia Stone]
  • A. Cynthia Stone chosen
    Cynthia Stone was an American actress best known for her work in early television and for her marriage to actor Jack Lemmon.
  • B. Cynthia Stevenson
    Cynthia Stevenson is an American actress known for her work in film and television, including roles in projects like "Home for the Holidays" and the series "Dead Like Me."
  • C. Cynthia Blaise
    Cynthia Blaise is an American dialect coach and actress known for her work on films such as "Bad Teacher" and "The Tiger Hunter."
  • D. Cynthia Potter
    Cynthia Potter is a fictional character appearing in the classic 1938 Mickey Rooney film "Love Finds Andy Hardy."
  • E. Cynthia Solomon
    Cynthia Solomon is a pioneering computer scientist and educator best known for her foundational work in the development of educational programming languages for children, including co-creating Logo.
  • 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_69d381c733c08190ab1dd6239f5f34ae completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d50a582be48190856c6f272eea4dcf completed April 7, 2026, 1:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6d5e2b0408190866bbe9a3a56928b completed May 3, 2026, 4:58 a.m.
Created at: April 6, 2026, 12:32 p.m.