Triple
T27111173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dravidian cultural region |
E686715
|
entity |
| Predicate | hasMajorDanceForm |
P66999
|
FINISHED |
| Object | Bharatanatyam |
—
|
NE NERFINISHED |
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: Bharatanatyam | Statement: [Dravidian cultural region, hasMajorDanceForm, Bharatanatyam]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMajorDanceForm Context triple: [Dravidian cultural region, hasMajorDanceForm, Bharatanatyam]
-
A.
hasDanceFormation
Indicates that an entity participates in or is arranged into a specific dance formation.
-
B.
usesDanceForms
chosen
Indicates that one entity employs or incorporates specific dance forms in its actions, practices, or expressions.
-
C.
hasChoreographicCharacteristics
Indicates that something possesses specific features, qualities, or attributes related to choreography or choreographic style.
-
D.
hasDanceMovement
Indicates that one entity includes, performs, or is characterized by a specific dance movement associated with another entity.
-
E.
hasDanceEnsemble
Indicates that an entity is associated with or includes a particular dance ensemble as part of its activities or composition.
- 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_69ef148accd48190b6ed6e13a15f2a4f |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69fdd07a34c08190982b8c61c2775cf6 |
completed | May 8, 2026, noon |
| PD | Predicate disambiguation | batch_69fdbd25c7908190b72fca8de7ce503f |
completed | May 8, 2026, 10:38 a.m. |
Created at: April 27, 2026, 8:54 a.m.