Triple
T25230195
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Badagu Thittu |
E632199
|
entity |
| Predicate | isNorthernVariantOf |
P11942
|
FINISHED |
| Object | Yakshagana |
—
|
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: Yakshagana | Statement: [Badagu Thittu, isNorthernVariantOf, Yakshagana]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isNorthernVariantOf Context triple: [Badagu Thittu, isNorthernVariantOf, Yakshagana]
-
A.
regionalVariantOf
chosen
Indicates that one entity is a version or form of another that is specific to a particular geographic region or locale.
-
B.
northernPartKnownAs
Indicates that the northern portion of an entity is referred to by a particular name or designation.
-
C.
northernTerminusVariant
Indicates that one location or feature serves as an alternative or variant northern endpoint of a route, line, or path.
-
D.
northernContinuationOf
Indicates that one entity is a direct geographic or structural continuation of another entity toward the north.
-
E.
isNorthernmostRegionOf
Indicates that one region is the geographically furthest north among all regions within a specified larger area or 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_69e75a8e0f688190a7aebe9a4815e25b |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f47cc7199c8190bf32bd5aa0090e07 |
completed | May 1, 2026, 10:13 a.m. |
| PD | Predicate disambiguation | batch_69f44d849e7c81909945438f40e35362 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 21, 2026, 1:04 p.m.