Triple
T20342838
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hare Krishna maha-mantra |
E495782
|
entity |
| Predicate | corePracticeOf |
P133670
|
FINISHED |
| Object | ISKCON devotees |
—
|
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: ISKCON devotees | Statement: [Hare Krishna maha-mantra, corePracticeOf, ISKCON devotees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: corePracticeOf Context triple: [Hare Krishna maha-mantra, corePracticeOf, ISKCON devotees]
-
A.
publicPractice
Indicates that an activity, behavior, or belief is carried out openly in public or within a community setting rather than privately.
-
B.
coversPractice
Indicates that one entity includes, addresses, or provides instruction on a particular practice or set of practices.
-
C.
featuresPractice
chosen
Indicates that something includes or offers a particular practice as a notable component or activity.
-
D.
settingOfPractice
Indicates the context or environment in which a particular practice, activity, or procedure is carried out.
-
E.
supportedPractice
Indicates that one entity endorses, promotes, or facilitates the use of a particular practice by 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_69e0b4a3320881909495ae8bc30bc2dc |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67836b72081908be65115abdb37bf |
completed | April 20, 2026, 7:02 p.m. |
| PD | Predicate disambiguation | batch_69e57636b4808190bc2855af48a3ccdc |
completed | April 20, 2026, 12:41 a.m. |
Created at: April 16, 2026, 11:24 a.m.