Triple
T17688264
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emma Newton |
E440952
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Alma Reville |
—
|
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: Alma Reville | Statement: [Emma Newton, creator, Alma Reville]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alma Reville Context triple: [Emma Newton, creator, Alma Reville]
-
A.
Alma Reville
chosen
Alma Reville was a British screenwriter, editor, and assistant director best known for her long creative collaboration with and marriage to filmmaker Alfred Hitchcock.
-
B.
Thelma Oliver
Thelma Oliver was an American actress and dancer best known for her role in the groundbreaking 1964 film "The Pawnbroker."
-
C.
Johanna Mankiewicz Davis
Johanna Mankiewicz Davis was an American novelist and screenwriter, and the daughter of acclaimed screenwriter Herman J. Mankiewicz.
-
D.
Ruth Wells
Ruth Wells was the wife of three-time Academy Award–winning American character actor Walter Brennan.
-
E.
Barbara Covett
Barbara Covett is a lonely, manipulative schoolteacher whose obsessive fixation on a colleague drives the psychological drama of "Notes on a Scandal."
- 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_69d8b9e940b081908b862bb0e6e89b0d |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4704944d8819089b153aa14839fc0 |
completed | April 19, 2026, 6:03 a.m. |
Created at: April 10, 2026, 10:03 a.m.