Triple
T25250655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spandakārikāḥ |
E632731
|
entity |
| Predicate | meditativeFocus |
P22925
|
FINISHED |
| Object | inner vibration between two thoughts or perceptions |
—
|
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: inner vibration between two thoughts or perceptions | Statement: [Spandakārikāḥ, meditativeFocus, inner vibration between two thoughts or perceptions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: meditativeFocus Context triple: [Spandakārikāḥ, meditativeFocus, inner vibration between two thoughts or perceptions]
-
A.
meditationType
Indicates the specific kind or category of meditation practice associated with an entity.
-
B.
meditationSubject
chosen
Indicates that one entity is the topic, focus, or object upon which another entity meditates.
-
C.
comfortFocus
Indicates that one entity directs its attention or efforts toward providing comfort or emotional ease to another entity.
-
D.
hasMeditativeSound
Indicates that something produces or is associated with a sound conducive to meditation or meditative practice.
-
E.
hasMeditativeGrooves
Indicates that something features grooves or patterns specifically designed to facilitate or enhance meditative or contemplative experiences.
- 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_69e75a8fdd3881909ba0b05aa5da92a7 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f4808ac0cc8190b19571d4c71b3025 |
completed | May 1, 2026, 10:29 a.m. |
| PD | Predicate disambiguation | batch_69f44d849e7c81909945438f40e35362 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 21, 2026, 1:11 p.m.