Triple
T13517064
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Medusa Film |
E322787
|
entity |
| Predicate | hasDistributedIn |
P8091
|
FINISHED |
| Object | cinemas |
—
|
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: cinemas | Statement: [Medusa Film, hasDistributedIn, cinemas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDistributedIn Context triple: [Medusa Film, hasDistributedIn, cinemas]
-
A.
isDistributedThrough
Indicates that something is supplied, circulated, or made available to others via a particular channel, medium, or distribution mechanism.
-
B.
laterDistributedOn
Indicates that something was distributed or made available at a time later than a referenced distribution or event date.
-
C.
distributesIn
chosen
Indicates that one entity allocates or hands out something (e.g., items, resources, information) within or across a specified area, group, or context.
-
D.
distributorOfWorkAppearedIn
Indicates that one entity is the distributor responsible for releasing or making available a particular work in which another entity appeared.
-
E.
hasDistributionRights
Indicates that one entity is legally authorized to distribute another entity’s product, content, or service within specified terms or territories.
- 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_69d80766a21881909f21a1b7421d3b8a |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbafa0ed508190b2855171b1945e84 |
completed | April 12, 2026, 2:43 p.m. |
| PD | Predicate disambiguation | batch_69dbae0b63748190b5e207f84b2532ea |
completed | April 12, 2026, 2:36 p.m. |
Created at: April 9, 2026, 9:44 p.m.