Triple
T23406424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carol (2015 film) |
E559946
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Phyllis Nagy |
—
|
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: Phyllis Nagy | Statement: [Carol (2015 film), screenwriter, Phyllis Nagy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Phyllis Nagy Context triple: [Carol (2015 film), screenwriter, Phyllis Nagy]
-
A.
Phyllis Nagy
chosen
Phyllis Nagy is an American screenwriter, director, and playwright best known for her Academy Award–nominated adaptation of Patricia Highsmith’s novel into the film "Carol."
-
B.
Elizabeth Swados
Elizabeth Swados was an American composer, writer, and director known for her innovative, socially engaged musical theater works on and off Broadway.
-
C.
Nancy Huston
Nancy Huston is a Canadian-born French-language novelist and essayist known for her explorations of identity, memory, and language.
-
D.
Phil Parmet
Phil Parmet is an American cinematographer known for his work on genre films, including Rob Zombie’s horror movie "The Devil’s Rejects."
-
E.
Joan Porter
Joan Porter is known as the wife of William A. Porter, the co-founder of the online brokerage firm E*TRADE.
- 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a50e607c8190ba0a22e89862a2d9 |
completed | April 29, 2026, 6:28 a.m. |
Created at: April 17, 2026, 5:38 p.m.