Triple
T23206743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York City (setting of Ghost) |
E580477
|
entity |
| Predicate | genreOfWorkUsedIn |
P89582
|
FINISHED |
| Object | romantic fantasy film |
—
|
LITERAL 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: romantic fantasy film | Statement: [New York City (setting of Ghost), genreOfWorkUsedIn, romantic fantasy film]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: genreOfWorkUsedIn Context triple: [New York City (setting of Ghost), genreOfWorkUsedIn, romantic fantasy film]
-
A.
genreOfWorkDescribedIn
Indicates that a work is characterized as belonging to a particular genre as described in another resource or context.
-
B.
genreOfWorkPerformedIn
Indicates that a specified genre characterizes the type of work that is performed in a particular event, context, or setting.
-
C.
genreOfWorkAbout
Indicates that a work is about a particular genre, expressing that the work’s subject matter or focus concerns that genre.
-
D.
genreOfWorkContributedTo
Indicates that an entity contributed to a work belonging to a specified genre.
-
E.
genreOfWorkSetting
chosen
Indicates the genre category that characterizes the setting in which a work takes place.
- F. None of above.
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_69e24602ae1481908aaa6bc7ca493867 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1907cd62c8190afee1e963b170727 |
completed | April 29, 2026, 5 a.m. |
| PD | Predicate disambiguation | batch_69effcccee508190a7ae311fdd319806 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:07 p.m.