Triple
T1518179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Searchlight Pictures |
E32167
|
entity |
| Predicate | distributorType |
P29986
|
FINISHED |
| Object | specialty film distributor |
—
|
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: specialty film distributor | Statement: [Searchlight Pictures, distributorType, specialty film distributor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distributorType Context triple: [Searchlight Pictures, distributorType, specialty film distributor]
-
A.
distributor
Indicates that an entity is responsible for supplying, delivering, or making another entity’s products or materials available to others.
-
B.
distributesIn
Indicates that one entity allocates or hands out something (e.g., items, resources, information) within or across a specified area, group, or context.
-
C.
distributorCountry
Indicates the country in which the distributor of an item, product, or work is located or operates.
-
D.
distributionToPartners
Indicates the allocation or transfer of resources, benefits, or proceeds from a source entity to its partner entities.
-
E.
allowsDistribution
Indicates that one entity grants permission for another entity to distribute or disseminate something (e.g., content, products, or data).
- F. None of above. chosen
Provenance (4 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_69a885e8caf88190a5fbb6159ce87786 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a9396e16408190b5e7b0ac43376d81 |
completed | March 5, 2026, 8:06 a.m. |
| PD | Predicate disambiguation | batch_69a907aa67cc81909f00135365447399 |
completed | March 5, 2026, 4:33 a.m. |
| PDg | Predicate description generation | batch_69a9396d3e1081909aa269b42041c357 |
completed | March 5, 2026, 8:06 a.m. |
Created at: March 4, 2026, 7:26 p.m.