Triple
T38664229
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nirguna Bhakti |
E940409
|
entity |
| Predicate | viewsScripture |
P2324
|
FINISHED |
| Object | as pointer to formless truth, not final description |
—
|
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: as pointer to formless truth, not final description | Statement: [Nirguna Bhakti, viewsScripture, as pointer to formless truth, not final description]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: viewsScripture Context triple: [Nirguna Bhakti, viewsScripture, as pointer to formless truth, not final description]
-
A.
hasViewOnScripture
chosen
Indicates that an entity holds a particular interpretive stance or doctrinal position regarding scripture.
-
B.
scriptureFor
Indicates that one entity serves as a scriptural or authoritative religious text for another entity (such as a person, group, or belief system).
-
C.
scriptureFocus
Indicates that something centers on, emphasizes, or is primarily concerned with religious scripture or sacred texts.
-
D.
scriptureRead
Indicates that an entity reads, studies, or engages with a religious or sacred text.
-
E.
inScripture
Indicates that something is mentioned, described, or referenced within a scriptural or sacred text.
- 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_69f76edfde348190bf6529d9f49ecd62 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fce545fec881909247a3af821d21ae |
completed | May 7, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69fce12eaeec81908cf81346b2cef6e0 |
completed | May 7, 2026, 6:59 p.m. |
Created at: May 3, 2026, 4:33 p.m.