Triple

T4386937
Position Surface form Disambiguated ID Type / Status
Subject Roma Downey E99265 entity
Predicate name P16 FINISHED
Object Roma Downey E99265 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: Roma Downey | Statement: [Roma Downey, name, Roma Downey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roma Downey
Context triple: [Roma Downey, name, Roma Downey]
  • A. Roma Downey chosen
    Roma Downey is an Irish actress and producer best known for her starring role on the television series "Touched by an Angel" and for producing faith-based film and TV projects.
  • B. Erica Durance
    Erica Durance is a Canadian actress best known for playing Lois Lane on the television series "Smallville."
  • C. Dorit Rhys
    Dorit Rhys was the wife of Victor Hope, 2nd Marquess of Linlithgow, a prominent British colonial administrator and Viceroy of India.
  • D. Alex Kingston
    Alex Kingston is an English actress best known for her roles in the television series "ER" and "Doctor Who," as well as numerous film and stage productions.
  • E. Lalla Ward
    Lalla Ward is an English actress and author best known for playing the Time Lady Romana in the long-running British science fiction series Doctor Who.
  • 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_69b3454f739481909ff6c28331f0c0b9 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b352669f608190b3aa7030d8073e04 completed March 12, 2026, 11:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5e52a0488819081fe724d592d8fdf completed March 14, 2026, 10:46 p.m.
Created at: March 12, 2026, 11:19 p.m.