Triple

T14513643
Position Surface form Disambiguated ID Type / Status
Subject Catelyn Stark E340461 entity
Predicate portrayedBy P1507 FINISHED
Object Michelle Fairley E340462 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: Michelle Fairley | Statement: [Catelyn Stark, portrayedBy, Michelle Fairley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michelle Fairley
Context triple: [Catelyn Stark, portrayedBy, Michelle Fairley]
  • A. Michelle Fairley chosen
    Michelle Fairley is a Northern Irish actress best known for playing Catelyn Stark in the television series "Game of Thrones."
  • B. Lena Headey
    Lena Headey is an English actress best known for playing Cersei Lannister in the television series "Game of Thrones."
  • C. Helena Carter
    Helena Carter was an American film actress known for her roles in 1940s and 1950s Hollywood productions, particularly in science fiction and adventure films.
  • D. Morven Christie
    Morven Christie is a Scottish actress known for her work in British television dramas, films, and theatre, including prominent roles in series such as "The A Word," "Grantchester," and "The Bay."
  • E. Tessa Menzies
    Tessa Menzies is a child of California politician and governor Gavin Newsom.
  • 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_69d822d9c0408190b9a2b3643e58bb4d completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69de9a6d82988190b6f957012bcc63d4 completed April 14, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6da64db881909a4f88d18031cb0c completed May 8, 2026, 4:59 a.m.
Created at: April 10, 2026, 1:21 a.m.