Triple
T36893166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Yablans Presentations |
E911810
|
entity |
| Predicate | associatedWithRoleOfFounder |
P133734
|
FINISHED |
| Object | film producer |
—
|
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: film producer | Statement: [Frank Yablans Presentations, associatedWithRoleOfFounder, film producer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithRoleOfFounder Context triple: [Frank Yablans Presentations, associatedWithRoleOfFounder, film producer]
-
A.
workIncludesRoleOfFounder
Indicates that a work involves or credits an entity in the specific role of founder.
-
B.
hasCoFounderRoleOf
Indicates that one entity holds the role or position of co-founder in relation to another entity, such as an organization or venture.
-
C.
founderRole
Indicates that an entity serves as a founder in relation to another entity, specifying the role or capacity in which they established it.
-
D.
hasFounderRelationship
Indicates a relationship where one entity serves as the founder or co-founder of another entity.
-
E.
associatedWorkOfFounder
chosen
Indicates a relationship where a work (such as a publication, project, or creation) is linked to the person who founded or established it.
- 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_69f76e8335908190b77e7e11d0e80820 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a10036481909c71188b2a0e7f04 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:13 p.m.