Triple
T30978856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Filmverlag der Autoren |
E789307
|
entity |
| Predicate | supportedCreators |
P290
|
FINISHED |
| Object | auteur filmmakers |
—
|
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: auteur filmmakers | Statement: [Filmverlag der Autoren, supportedCreators, auteur filmmakers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportedCreators Context triple: [Filmverlag der Autoren, supportedCreators, auteur filmmakers]
-
A.
supportsCreatorType
Indicates that something is compatible with, designed for, or able to work with a specified type or category of creator.
-
B.
supportedCreationOf
chosen
Indicates that one entity actively aided, endorsed, or facilitated the bringing into existence or establishment of another entity.
-
C.
usedByCreators
Indicates that something is utilized or employed by creators in their work or activities.
-
D.
supportedComposer
Indicates that one entity provided backing, resources, or advocacy that helped another entity (a composer) create, develop, or promote their musical work.
-
E.
supportsAnalyticsForCreators
Indicates that an entity provides tools or functionality that enable creators to access and use analytics about their content or audience.
- 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_69f224c4831c8190be53924ec25a150a |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a037c876524819098545e6037d3107d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379e5174c8190a0bdde7e381b7624 |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 29, 2026, 8:55 p.m.