Triple

T14780581
Position Surface form Disambiguated ID Type / Status
Subject Ygritte E347378 entity
Predicate portrayedBy P1507 FINISHED
Object Rose Leslie E267913 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: Rose Leslie | Statement: [Ygritte, portrayedBy, Rose Leslie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rose Leslie
Context triple: [Ygritte, portrayedBy, Rose Leslie]
  • A. Rose Leslie chosen
    Rose Leslie is a Scottish actress best known for her roles in the TV series "Game of Thrones" and "Downton Abbey," as well as various film and television projects.
  • B. Emma Tennant
    Emma Tennant was a British novelist known for her experimental, often fantastical fiction and for reimagining classic literary works.
  • C. Katheryn Winnick
    Katheryn Winnick is a Canadian actress best known for her role as the fierce shield-maiden Lagertha in the television series "Vikings" and for appearances in various film and TV productions.
  • D. Tessa Menzies
    Tessa Menzies is a child of California politician and governor Gavin Newsom.
  • E. Jane Wenham
    Jane Wenham was a British actress known for her work in mid-20th-century film, television, and theatre.
  • 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deca9c7cac8190ba900df95e42e318 completed April 14, 2026, 11:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe24b626c48190a6aa9eda43539246 completed May 8, 2026, 6 p.m.
Created at: April 10, 2026, 1:31 a.m.