Triple
T1083480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nepali |
E23998
|
entity |
| Predicate | usedInScripture |
P11163
|
FINISHED |
| Object | Hindu religious texts in Nepal |
—
|
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: Hindu religious texts in Nepal | Statement: [Nepali, usedInScripture, Hindu religious texts in Nepal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedInScripture Context triple: [Nepali, usedInScripture, Hindu religious texts in Nepal]
-
A.
scripturalUse
Indicates that one entity is used as a scriptural reference, source, or basis within the context or content of another entity.
-
B.
inScripture
chosen
Indicates that something is mentioned, described, or referenced within a scriptural or sacred text.
-
C.
hasScripture
Indicates that one entity possesses, is associated with, or is defined by a particular scripture or set of scriptural texts.
-
D.
scripturalReference
Indicates that one entity cites, alludes to, or is based on a specific passage or portion of a scriptural text found in another entity.
-
E.
scriptureFor
Indicates that one entity serves as a scriptural or authoritative religious text for another entity (such as a person, group, or belief system).
- 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_69a49404428c819092dcc9632f5f7b8b |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b95e56948190a1e92367ad7240b7 |
completed | March 1, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69a4b73f4310819086281f8ec67d1a32 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.