Triple
T21295513
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mahapuranas |
E524909
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Hindu scripture collection |
C22098
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: Hindu scripture collection Context triple: [Mahapuranas, instanceOf, Hindu scripture collection]
-
A.
Hindu religious texts
chosen
Hindu religious texts are a diverse body of ancient and medieval scriptures—including the Vedas, Upanishads, epics like the Mahabharata and Ramayana, and numerous Puranas and devotional works—that articulate Hindu philosophy, mythology, rituals, and ethical teachings.
-
B.
Hindu technical scripture
A Hindu technical scripture is a specialized sacred text that systematically presents practical knowledge—such as ritual procedures, architecture, arts, sciences, or governance—within a Hindu religious and philosophical framework.
-
C.
Upanishads collection
A curated set of ancient Indian philosophical texts from the Upanishads, organized for study, reference, and comparative exploration of their teachings.
-
D.
Tibetan Buddhist text collection
A Tibetan Buddhist text collection is an organized compilation of canonical and commentarial writings—such as sutras, tantras, philosophical treatises, and ritual manuals—preserved in Tibetan language and script for study, practice, and transmission of the Buddhist tradition.
-
E.
Vaishnava scriptures
Vaishnava scriptures are sacred Hindu texts that focus on the worship, teachings, and stories of Vishnu and his avatars, guiding devotees in theology, devotion, and practice.
- F. None of above.
Provenance (1 batch)
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_69e0b517e6748190850d6f6ddf323d69 |
completed | April 16, 2026, 10:08 a.m. |
Created at: April 16, 2026, 4:04 p.m.