Triple
T35624007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metrocolor |
E1029397
|
entity |
| Predicate | filmStockSupplier |
P143064
|
FINISHED |
| Object | Eastman Kodak |
—
|
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: Eastman Kodak | Statement: [Metrocolor, filmStockSupplier, Eastman Kodak]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmStockSupplier Context triple: [Metrocolor, filmStockSupplier, Eastman Kodak]
-
A.
filmStudioLot
Indicates a relationship where a film studio owns, operates, or is associated with a specific studio lot or production facility.
-
B.
filmStockType
chosen
Indicates the specific type or category of photographic or motion picture film stock used or associated with an entity.
-
C.
distributorOfWorkFeaturing
Indicates that one entity distributes or makes available a work in which another entity is featured or appears.
-
D.
distributesFilmsFor
Indicates that one entity handles the distribution of films on behalf of another entity.
-
E.
distributorOfWorkAppearedIn
Indicates that one entity is the distributor responsible for releasing or making available a particular work in which another entity appeared.
- 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_69f76e0709408190bbe322bf1707ef6b |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79ef3d120819084fb33df17a73b15 |
completed | May 3, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_69f79e4bdbcc8190be7a0d2cf8a77b64 |
completed | May 3, 2026, 7:13 p.m. |
Created at: May 3, 2026, 4:05 p.m.