Triple
T5273638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gremlins (1984 film score) |
E119320
|
entity |
| Predicate | partOfGenre |
P33225
|
FINISHED |
| Object | horror-comedy film music |
—
|
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: horror-comedy film music | Statement: [Gremlins (1984 film score), partOfGenre, horror-comedy film music]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfGenre Context triple: [Gremlins (1984 film score), partOfGenre, horror-comedy film music]
-
A.
genreWithin
Indicates that one genre is a subgenre or more specific category contained within another, broader genre.
-
B.
genre
Indicates the artistic or thematic category to which a work (such as a book, film, or song) belongs.
-
C.
coveredInGenre
chosen
Indicates that a work or item is associated with, categorized under, or treated within a particular genre.
-
D.
genreOfAppearance
Indicates the genre or type of creative work in which an entity appears.
-
E.
subgenre
Indicates that one genre is a more specific, subordinate category within a broader parent genre.
- 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_69bd446c38e081908cdaf113bdf86790 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7d5a23908190a24e79d1b29d6fcf |
completed | March 20, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69bd77c71268819094f9f5203eed392d |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:51 p.m.