Triple
T38018423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dharmaguptaka |
E948555
|
entity |
| Predicate | vinayaCatalogNumber |
P142997
|
FINISHED |
| Object | Taishō Tripiṭaka T1428–T1453 |
—
|
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: Taishō Tripiṭaka T1428–T1453 | Statement: [Dharmaguptaka, vinayaCatalogNumber, Taishō Tripiṭaka T1428–T1453]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vinayaCatalogNumber Context triple: [Dharmaguptaka, vinayaCatalogNumber, Taishō Tripiṭaka T1428–T1453]
-
A.
vinayaLanguage
Indicates that the subject uses, is expressed in, or is associated with the Vinaya (Buddhist monastic discipline) as a language or linguistic tradition.
-
B.
vinayaPreservedIn
chosen
Indicates that a body of Vinaya (monastic disciplinary rules) is preserved, transmitted, or contained within a particular text, collection, or tradition.
-
C.
inBuddhistCanon
Indicates that something is included within, or recognized as part of, the Buddhist canonical scriptures.
-
D.
numberOfSutras
Indicates the quantity or count of sutras associated with a given entity.
-
E.
TripitakaKoreanaNumberOfBlocks
Indicates the quantity of individual printing blocks associated with the Tripitaka Koreana.
- 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_69f76efc10448190aff5fb566b98f952 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fcc42cbac48190b8d3e4c9ce140838 |
completed | May 7, 2026, 4:56 p.m. |
| PD | Predicate disambiguation | batch_69fcb0fc69c88190800453eb57a7e62c |
completed | May 7, 2026, 3:34 p.m. |
Created at: May 3, 2026, 4:20 p.m.