Triple
T25961132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vaishakha |
E645539
|
entity |
| Predicate | hasObservance |
P126917
|
FINISHED |
| Object | Ganga Snan during Vaishakha |
—
|
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: Ganga Snan during Vaishakha | Statement: [Vaishakha, hasObservance, Ganga Snan during Vaishakha]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasObservance Context triple: [Vaishakha, hasObservance, Ganga Snan during Vaishakha]
-
A.
hasTypeOfObservance
Indicates that an observance is classified under a specific type or category of observance.
-
B.
observanceRequires
Indicates that carrying out a particular observance or practice is contingent upon, or must be accompanied by, the fulfillment of a specified requirement or condition.
-
C.
observance
Indicates the performance or maintenance of a practice, rule, or custom in accordance with prescribed or expected standards.
-
D.
observanceLinkedTo
chosen
Indicates a relationship where a particular observance (such as a ritual, ceremony, or commemorative act) is connected or associated with another entity, event, or concept.
-
E.
hasObservation
Indicates that an entity records, contains, or is associated with a specific observation or measured instance.
- 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_69e77e85efc08190997da7fcf98bd300 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f604c60fe0819092ad09d1c5b0c100 |
completed | May 2, 2026, 2:05 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 22, 2026, 8:47 a.m.