Triple
T34436636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brian Walker |
E883974
|
entity |
| Predicate | hasCoStarInWork |
—
|
GENERATED |
| Object | Diana Ross |
—
|
UNRECOGNIZED GENERATED |
How this triple was built (1 step)
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.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCoStarInWork Context triple: [Brian Walker, hasCoStarInWork, Diana Ross]
-
A.
hasCoStarHumanCharacter
chosen
Indicates that a human character appears as a co-star alongside another character in the same work or production.
-
B.
hasPartnerInWork
Indicates that one entity collaborates professionally or is partnered with another entity in a work-related context.
-
C.
hasWorksIn
Indicates that one entity is employed by or performs their professional activities within the organization, location, or context represented by another entity.
-
D.
hasWorkUsedFor
Indicates that a particular work (e.g., document, resource, or artifact) is utilized for a specific purpose, task, or activity.
-
E.
hasCollaborationIn
Indicates that two or more entities work together or jointly participate in a specific project, context, or domain.
- F. None of above.
Provenance (1 batch)
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_69f349c548d88190978e2a82502c03d0 |
completed | April 30, 2026, 12:23 p.m. |
Created at: May 1, 2026, 2 a.m.