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.