Triple

T15483899
Position Surface form Disambiguated ID Type / Status
Subject Kate O'Mara E376991 entity
Predicate relative P37 FINISHED
Object Belinda Carroll E1195662 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: Belinda Carroll | Statement: [Kate O'Mara, relative, Belinda Carroll]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Belinda Carroll
Context triple: [Kate O'Mara, relative, Belinda Carroll]
  • A. Belinda Carroll chosen
    Belinda Carroll is a British actress known for her work on stage and screen, and as the sister of fellow actress Kate O'Mara.
  • B. Caroline Ross
    Caroline Ross is a film editor known for her work on the science fiction movie "Starship Troopers."
  • C. Belinda Bromilow
    Belinda Bromilow is an Australian actress known for her work in television, film, and theatre, including a prominent role in the satirical historical series "The Great."
  • D. Beryl Franklin Carroll
    Beryl Franklin Carroll was an American politician who served as the 20th Governor of Iowa in the early 20th century.
  • E. Margaret Carroll
    Margaret Carroll is known primarily as the sister of acclaimed British actress Madeleine Carroll, a major film star of the 1930s and 1940s.
  • 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_69d85cd21dcc81908646251b1c26ea00 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03f8e6ff08190b130b3a38f4190e7 completed April 16, 2026, 1:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff78dab488190a89b9eb4f648b36c completed May 10, 2026, 3:12 a.m.
Created at: April 10, 2026, 3:45 a.m.