Triple
T29847660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Light Winter |
E757972
|
entity |
| Predicate | authorOtherRoles |
P84740
|
FINISHED |
| Object | director |
—
|
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: director | Statement: [Red Light Winter, authorOtherRoles, director]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: authorOtherRoles Context triple: [Red Light Winter, authorOtherRoles, director]
-
A.
coAuthorOccupation
Indicates that two or more co-authors share the same or closely related professional occupation.
-
B.
notableAuthorRole
Indicates that an entity holds a significant or distinguished role as an author in relation to another entity.
-
C.
authorOfAlso
Indicates that an entity is also an author of another specified work or item, in addition to any primary authorship already indicated.
-
D.
associatedWithAuthorRole
chosen
Indicates that an entity is connected to another entity specifically in the capacity or role of an author.
-
E.
authorOfCompanionWork
Indicates that one entity is the creator or writer of another entity that serves as a companion or supplementary work to a primary work.
- 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_69f2245a82cc8190a387e7d0118d710b |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fbaebc8f2c8190b94f1b4a3ec92e8c |
completed | May 6, 2026, 9:12 p.m. |
| PD | Predicate disambiguation | batch_69fbadf1e6008190a71bbd196ba06844 |
completed | May 6, 2026, 9:09 p.m. |
Created at: April 29, 2026, 5:42 p.m.