Triple
T4882528
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Classical Yoga |
E109362
|
entity |
| Predicate | acceptsConcept |
P531
|
FINISHED |
| Object | purusha |
—
|
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: purusha | Statement: [Classical Yoga, acceptsConcept, purusha]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: acceptsConcept Context triple: [Classical Yoga, acceptsConcept, purusha]
-
A.
hasConcept
chosen
Indicates that an entity includes, embodies, or is associated with a particular concept.
-
B.
acceptedIn
Indicates that something has been formally received, approved, or admitted into a particular context, group, or system.
-
C.
introducedConcept
Indicates that one entity is responsible for presenting, defining, or bringing a new concept into use or awareness for another entity or context.
-
D.
protectedConcept
Indicates that one entity is a concept or attribute that is legally or normatively safeguarded from discrimination, harm, or unauthorized use in relation to another entity.
-
E.
defendsConcept
Indicates that one entity actively supports and argues in favor of a particular concept, idea, or theory, often in response to criticism or challenge.
- 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_69bd440e9d64819083e82cf33b4d9570 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ddfff0c81908fb148a6f6508334 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2be5e881909f6ec9c3bcde49f3 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:27 p.m.