Triple
T7365216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sattriya dance |
E169852
|
entity |
| Predicate | usesCostumeType |
P5541
|
FINISHED |
| Object | traditional Assamese silk costumes |
—
|
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: traditional Assamese silk costumes | Statement: [Sattriya dance, usesCostumeType, traditional Assamese silk costumes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesCostumeType Context triple: [Sattriya dance, usesCostumeType, traditional Assamese silk costumes]
-
A.
haveDistinctCostume
Indicates that the entities each possess a costume that is different from the others’ costumes.
-
B.
costumeType
chosen
Indicates the specific kind or category of costume associated with an entity.
-
C.
isCostumed
Indicates that an entity is wearing or otherwise adorned with a costume.
-
D.
colorAssociatedWithCostume
Indicates that a particular color is thematically or typically linked to a specific costume.
-
E.
costumeContext
Indicates the situational or narrative context in which a costume is used, such as the event, setting, or role it is associated with.
- 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_69c68a5ade988190885b7175f63b7534 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f26d6d6081909c7272a9ccae0d97 |
completed | March 27, 2026, 9:11 p.m. |
| PD | Predicate disambiguation | batch_69c6f02d36108190bcb34a95e6a30bd7 |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:06 p.m.