Triple
T37087865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalbeliya tribe |
E918337
|
entity |
| Predicate | danceCostume |
P121561
|
FINISHED |
| Object | black swirling skirts |
—
|
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: black swirling skirts | Statement: [Kalbeliya tribe, danceCostume, black swirling skirts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: danceCostume Context triple: [Kalbeliya tribe, danceCostume, black swirling skirts]
-
A.
costume
Indicates that one entity is wearing, dressed in, or outfitted with the other entity as a costume.
-
B.
designedCostumesFor
Indicates that one entity created or planned the costumes used by another entity, typically for a performance, production, or event.
-
C.
costumeContext
Indicates the situational or narrative context in which a costume is used, such as the event, setting, or role it is associated with.
-
D.
costumeDesignEmphasisOn
Indicates that a costume design places particular focus or priority on a specified element, style, feature, or thematic aspect.
-
E.
stageCostume
chosen
Indicates that one entity is a costume specifically used or worn for a performance or stage production by another entity.
- 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_69f76e9952b88190a6fe01ba01476520 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb55de3b9c8190a7656aeab3c3ffbc |
completed | May 6, 2026, 2:53 p.m. |
| PD | Predicate disambiguation | batch_69fb35bc92e08190bff447624e2df791 |
completed | May 6, 2026, 12:36 p.m. |
Created at: May 3, 2026, 4:14 p.m.