Triple
T11861138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tiantai Buddhist temples |
E282159
|
entity |
| Predicate | practiceEmphasis |
P12790
|
FINISHED |
| Object | meditation |
—
|
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: meditation | Statement: [Tiantai Buddhist temples, practiceEmphasis, meditation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: practiceEmphasis Context triple: [Tiantai Buddhist temples, practiceEmphasis, meditation]
-
A.
practice
Indicates that an entity regularly performs an activity or skill, typically to improve proficiency or maintain competence.
-
B.
practiceType
chosen
Indicates the specific kind or category of practice associated with an entity or activity.
-
C.
skillEmphasis
Indicates that a particular skill is given special focus, priority, or importance within a context such as a role, task, or curriculum.
-
D.
trainingEmphasized
Indicates that particular training or instructional activities are given special focus, priority, or importance within a broader context or process.
-
E.
practiceElement
Indicates that one entity is a component, step, or sub-activity within a broader practice or procedure involving 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_69d6ab287ba48190a5178779fd19b9b7 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a69b16bc8190999a0c1240f9ce6a |
completed | April 10, 2026, 7:28 a.m. |
| PD | Predicate disambiguation | batch_69d8a2573dbc8190ab432e8e28fde6cc |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:43 p.m.