Triple
T5086943
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kumārila Bhaṭṭa |
E114659
|
entity |
| Predicate | acceptedPramāṇa |
P57100
|
FINISHED |
| Object | perception (pratyakṣa) |
—
|
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: perception (pratyakṣa) | Statement: [Kumārila Bhaṭṭa, acceptedPramāṇa, perception (pratyakṣa)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: acceptedPramāṇa Context triple: [Kumārila Bhaṭṭa, acceptedPramāṇa, perception (pratyakṣa)]
-
A.
acceptedPramana
chosen
Indicates that one entity has acknowledged and accepted another entity as a valid source of knowledge or authority.
-
B.
acceptedIn
Indicates that something has been formally received, approved, or admitted into a particular context, group, or system.
-
C.
approvedAs
Indicates that one entity has been officially accepted, authorized, or validated in a particular role, status, or capacity by another entity.
-
D.
approvedPractice
Indicates that a particular practice, method, or procedure has been formally reviewed and granted official approval for use or adoption.
-
E.
approvalMethod
Indicates the method or process by which approval is granted or obtained between entities.
- 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_69bd443e941881908eb4e8c685b6f656 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd751fb6dc8190be674c92a17e8c0e |
completed | March 20, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69bd7159adc881909effd4382c395c66 |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:40 p.m.