Triple

T8297616
Position Surface form Disambiguated ID Type / Status
Subject Tracy Bond E194260 entity
Predicate portrayedBy P1507 FINISHED
Object Diana Rigg E378877 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: Diana Rigg | Statement: [Tracy Bond, portrayedBy, Diana Rigg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diana Rigg
Context triple: [Tracy Bond, portrayedBy, Diana Rigg]
  • A. Diana Rigg chosen
    Diana Rigg was an acclaimed English actress best known for her roles as Emma Peel in the 1960s TV series "The Avengers" and Olenna Tyrell in "Game of Thrones."
  • B. Kate O'Mara
    Kate O'Mara was a British actress best known for her glamorous, often villainous roles in television dramas such as Dynasty and Doctor Who.
  • C. Glenda Jackson
    Glenda Jackson was an acclaimed British actress and Labour Party politician, renowned for her Oscar-winning film roles and later service as a Member of Parliament.
  • D. Fiona Shaw
    Fiona Shaw is an acclaimed Irish actress and theatre director known for her powerful stage performances and memorable film roles, including appearances in the Harry Potter series and numerous prestige dramas.
  • E. Vikki Heywood
    Vikki Heywood is a British arts executive best known for her leadership roles in major cultural institutions, including serving as executive director of the Royal Shakespeare Company.
  • 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_69ca82e50ebc81909aa7b260c76bd757 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7dfa040c8190ab801b3910e39142 completed March 31, 2026, 7:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce4d8a7eb48190bc1bebc56a46a5b9 completed April 2, 2026, 11:05 a.m.
Created at: March 30, 2026, 5:53 p.m.