Triple

T16146618
Position Surface form Disambiguated ID Type / Status
Subject Rene Russo as Kate Mullen E391800 entity
Predicate characterName P36851 FINISHED
Object Kate Mullen NE NERFINISHED

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: Kate Mullen | Statement: [Rene Russo as Kate Mullen, characterName, Kate Mullen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kate Mullen
Context triple: [Rene Russo as Kate Mullen, characterName, Kate Mullen]
  • A. Kate Mullen
    Kate Mullen is known as the wife of Tom Mullen.
  • B. Kate Mullen chosen
    Kate Mullen is the central protagonist of the work "Ransom," around whom the main narrative and its conflicts revolve.
  • C. Anne Mullen
    Anne Mullen is a notable individual distinguished enough to be recognized as a prominent bearer of the surname Mullen.
  • D. Lisa McGrillis
    Lisa McGrillis is a British actress known for her work in television, film, and theatre, including roles in series like "Inspector George Gently" and "Mum."
  • E. Kate Nelligan
    Kate Nelligan is a Canadian actress acclaimed for her work in film, television, and theatre, noted for her intense dramatic performances and multiple award nominations.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d87f1c65e48190aa2b4c472e9bafc4 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21d947e68819081b4b7c757ce71b6 completed April 17, 2026, 11:46 a.m.
Created at: April 10, 2026, 5:01 a.m.