Triple
T37913657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 曹洞宗 |
E945751
|
entity |
| Predicate | 教義的キーワード |
P101793
|
FINISHED |
| Object | 只管打坐 |
—
|
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: 只管打坐 | Statement: [曹洞宗, 教義的キーワード, 只管打坐]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 教義的キーワード Context triple: [曹洞宗, 教義的キーワード, 只管打坐]
-
A.
doctrinalTerm
chosen
Indicates that one entity is a doctrinal or theological term that conceptually characterizes, labels, or defines the other entity within a religious or ideological system.
-
B.
doctrinalTheme
Indicates that one entity concerns, expresses, or is characterized by a particular doctrinal or theological theme in relation to another.
-
C.
theologicalConcept
Indicates that something is a religious or theological idea, doctrine, or principle within a belief system.
-
D.
doctrinalFoundationFor
Indicates that one doctrine, principle, or teaching serves as the fundamental basis or supporting rationale for another.
-
E.
doctrinalEmphasis
Indicates a relationship where a doctrine, belief system, or teaching is given particular focus, priority, or stress within a religious, ideological, or organizational 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_69f76ef2ebd88190be5229f2621070b3 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc36ce1f88190a7fa1656b714e107 |
completed | May 6, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69fbbd166a488190b1bf9316b0790801 |
completed | May 6, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:20 p.m.