Triple
T23658384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sandhi Puja |
E584371
|
entity |
| Predicate | associatedFormOfDurga |
P92870
|
FINISHED |
| Object | Chamunda |
—
|
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: Chamunda | Statement: [Sandhi Puja, associatedFormOfDurga, Chamunda]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedFormOfDurga Context triple: [Sandhi Puja, associatedFormOfDurga, Chamunda]
-
A.
associatedFormOfShiva
Indicates a relationship where one entity is a particular form, aspect, or manifestation that is traditionally associated with the deity Shiva.
-
B.
associatedFormOfVishnu
Indicates a relationship where something is linked or connected as a particular form or manifestation of Vishnu.
-
C.
associatedGoddess
chosen
Indicates that one entity is recognized as the goddess traditionally linked or connected to another entity (such as a place, concept, or deity).
-
D.
associatedWithAvatarOfVishnu
Indicates a relationship in which something is connected, linked, or related to an avatar (incarnation) of the deity Vishnu.
-
E.
associatedDeityOrForce
Indicates that one entity is linked to, represented by, or under the influence of a particular deity or supernatural force.
- 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_69e248ffc0888190ae23c4731eb8b7ac |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b35ce4bc81909a26bc7e44a929d8 |
completed | April 29, 2026, 7:29 a.m. |
| PD | Predicate disambiguation | batch_69f118d7903c8190bb590a71771e93af |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:49 p.m.