Triple
T10223046
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jyotirlinga of Shiva at Trimbakeshwar |
E242629
|
entity |
| Predicate | primaryOffering |
P34857
|
FINISHED |
| Object | bilva leaves |
—
|
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: bilva leaves | Statement: [Jyotirlinga of Shiva at Trimbakeshwar, primaryOffering, bilva leaves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryOffering Context triple: [Jyotirlinga of Shiva at Trimbakeshwar, primaryOffering, bilva leaves]
-
A.
primaryListing
Indicates that one item in a set of listings is designated as the main or most authoritative listing for a given entity or context.
-
B.
offering
Indicates that one entity presents or provides something to another entity, typically as a gift, contribution, or proposal.
-
C.
primaryAsset
Indicates that one entity is the main or most important asset associated with another entity.
-
D.
firstOffered
Indicates that one entity was the earliest or initial provider or proposer of something to another entity or context.
-
E.
offeringType
chosen
Indicates the category or nature of what is being offered in a transaction or interaction (e.g., product, service, or other type of offering).
- 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_69d381ae26c48190985abd0e25ee5d04 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d3aa8305e481908ee1fc1d9eda6fa0 |
completed | April 6, 2026, 12:43 p.m. |
| PD | Predicate disambiguation | batch_69d3955f61f88190b8d37ff645cd44d3 |
completed | April 6, 2026, 11:13 a.m. |
Created at: April 6, 2026, 11:10 a.m.