Triple
T36003996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nyingma–Kagyu–Sakya–Gelug traditions |
E1041212
|
entity |
| Predicate | sharesTextualCanonWith |
P16943
|
FINISHED |
| Object | Kangyur |
—
|
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: Kangyur | Statement: [Nyingma–Kagyu–Sakya–Gelug traditions, sharesTextualCanonWith, Kangyur]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesTextualCanonWith Context triple: [Nyingma–Kagyu–Sakya–Gelug traditions, sharesTextualCanonWith, Kangyur]
-
A.
sharesNewTestamentCanonWith
Indicates that two entities recognize and use the same set of New Testament canonical books.
-
B.
sharesScripturalTraditionWith
chosen
Indicates that two entities are connected by drawing on, recognizing, or being grounded in the same or closely related body of scriptural texts or religious canon.
-
C.
religiousCanonRelation
Indicates that one entity is part of, derived from, or otherwise related to the officially recognized religious canon of another entity.
-
D.
canonizedTogetherWith
Indicates that two or more individuals were officially canonized as saints in the same ceremony or decree.
-
E.
isAssociatedWithReligiousText
Indicates a relationship where an entity is connected or linked in some way to a religious text, such as being based on, derived from, or directly related to it.
- 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_69f76e2a02208190aedd1f9025a8b300 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a007aa8d3a481908543f9b5d562a90c |
completed | May 10, 2026, 12:31 p.m. |
| PD | Predicate disambiguation | batch_6a007a44996481908688ccfdbc56511d |
completed | May 10, 2026, 12:29 p.m. |
Created at: May 3, 2026, 4:07 p.m.