Triple
T9393655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Deeley |
E226087
|
entity |
| Predicate | hasRoleInCreation |
P161
|
FINISHED |
| Object | film producer of The Deer Hunter |
—
|
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 of The Deer Hunter | Statement: [Michael Deeley, hasRoleInCreation, film producer of The Deer Hunter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRoleInCreation Context triple: [Michael Deeley, hasRoleInCreation, film producer of The Deer Hunter]
-
A.
hasCreatorRoleFor
Indicates that an entity serves in the role of creator for another entity, establishing a creator-to-created relationship.
-
B.
hasCreation
Indicates a relationship where one entity is the creator or originator of another entity.
-
C.
hasRole
chosen
Indicates that an entity occupies, performs, or is assigned a specific role or function in relation to another entity or context.
-
D.
firstCreatorRole
Indicates the specific role or capacity in which the primary or earliest creator of an entity contributed to its creation.
-
E.
hasNotableRoleIn
Indicates that an entity holds a significant or noteworthy role or function within another entity, event, work, or context.
- 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_69ca842f7e3481908bf5bcf52e032dbd |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd510fec6481908b51c497744068c8 |
completed | April 1, 2026, 5:08 p.m. |
| PD | Predicate disambiguation | batch_69cca545b2448190a4297312e39c21ac |
completed | April 1, 2026, 4:55 a.m. |
Created at: March 30, 2026, 7:45 p.m.