Triple
T25282864
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shiva’s ganas |
E633863
|
entity |
| Predicate | mythologicalTextMention |
P158800
|
FINISHED |
| Object | Skanda Purana |
—
|
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: Skanda Purana | Statement: [Shiva’s ganas, mythologicalTextMention, Skanda Purana]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mythologicalTextMention Context triple: [Shiva’s ganas, mythologicalTextMention, Skanda Purana]
-
A.
mythologicalTextMention
chosen
Indicates that a mythological text mentions, references, or otherwise explicitly refers to a given entity or concept.
-
B.
mythologicalContent
Indicates that the subject contains, references, or is associated with myths, mythological narratives, or myth-based elements.
-
C.
linkedToMythology
Indicates that something has a connection or association with a mythological tradition, figure, story, or theme.
-
D.
mythologicalCategory
Indicates that one entity is classified as belonging to the mythological type, group, or category represented by the other entity.
-
E.
mythologicalRole
Indicates the specific function, duty, or status an entity holds within a mythological or legendary context.
- 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_69e75a9402fc81909362ca85277c06d9 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f497bc12b881908fe3386c66252bf6 |
completed | May 1, 2026, 12:08 p.m. |
| PD | Predicate disambiguation | batch_69f49377411c8190b2188de444d76795 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 21, 2026, 1:19 p.m.