Triple
T35640254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vivien’s Models |
E1029837
|
entity |
| Predicate | representedTalentType |
P166276
|
FINISHED |
| Object | fashion models |
—
|
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: fashion models | Statement: [Vivien’s Models, representedTalentType, fashion models]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: representedTalentType Context triple: [Vivien’s Models, representedTalentType, fashion models]
-
A.
talentType
chosen
Indicates the specific category or kind of talent or skill associated with an entity.
-
B.
performerType
Indicates the role or category of performer responsible for carrying out an action or participating in an event.
-
C.
typicalPerformerRoleType
Indicates the usual or characteristic role type that a performer commonly plays or is associated with in their performances.
-
D.
representedRole
Indicates that one entity serves as a stand-in, proxy, or representative performing a role on behalf of another entity.
-
E.
portrayedInWorkType
Indicates that an entity is depicted or represented within a work of a specified type (such as a film, book, painting, or other creative medium).
- 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_69f76e087bdc8190a4794bf9c0bd7634 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff56ef0a5c8190ae729d66a8cf7fc4 |
completed | May 9, 2026, 3:46 p.m. |
| PD | Predicate disambiguation | batch_69ff539859c481909ec56310da418688 |
completed | May 9, 2026, 3:32 p.m. |
Created at: May 3, 2026, 4:05 p.m.