Triple
T20975648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mangalnath Temple |
E516617
|
entity |
| Predicate | commonRitualLanguage |
P59986
|
FINISHED |
| Object | Sanskrit |
—
|
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: Sanskrit | Statement: [Mangalnath Temple, commonRitualLanguage, Sanskrit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commonRitualLanguage Context triple: [Mangalnath Temple, commonRitualLanguage, Sanskrit]
-
A.
languageUsedInRituals
chosen
Indicates that a particular language is employed as the medium of speech, chant, or recitation during specific rituals or ceremonial practices.
-
B.
audienceOfRituals
Indicates that an entity serves as the audience or observers for a particular ritual or set of rituals.
-
C.
relatedRitual
Indicates that one entity is associated with, connected to, or involved in the performance or context of a particular ritual.
-
D.
usesRitually
Indicates that an entity employs or performs something as part of a ritual or ceremonial practice.
-
E.
ritualSignificance
Indicates that something holds special importance or meaning within a ritual or ceremonial 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_69e0b4fee5ac8190875fa9ceba1a5e5e |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fba3df2081908c1db5f8610ba43d |
completed | April 21, 2026, 4:23 a.m. |
| PD | Predicate disambiguation | batch_69e5dbe6976081908abd4e9c8734bae9 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:46 p.m.