Triple
T453432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guiyuan Temple |
E7179
|
entity |
| Predicate | hasScriptureCollection |
P11799
|
FINISHED |
| Object | Buddhist sutras |
—
|
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: Buddhist sutras | Statement: [Guiyuan Temple, hasScriptureCollection, Buddhist sutras]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasScriptureCollection Context triple: [Guiyuan Temple, hasScriptureCollection, Buddhist sutras]
-
A.
hasScripture
Indicates that one entity possesses, is associated with, or is defined by a particular scripture or set of scriptural texts.
-
B.
hasViewOnScripture
Indicates that an entity holds a particular interpretive stance or doctrinal position regarding scripture.
-
C.
hasLanguageOfScripture
Indicates that an entity’s scriptural or sacred texts are written or expressed in a specified language.
-
D.
hasSacredText
Indicates that an entity possesses or is associated with a particular sacred or religious text.
-
E.
scripturalCorpus
chosen
Indicates that one entity is a body of scriptural or sacred texts associated with, or serving as the canonical writings for, another entity.
- 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_69a2e7e4676c81909ea0dbdecac0687c |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ef866e848190a5b700250ec56256 |
completed | Feb. 28, 2026, 1:37 p.m. |
| PD | Predicate disambiguation | batch_69a2ede3187c8190a7ced078f0ec3476 |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.