Triple
T26125167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brahma Sampradaya |
E659079
|
entity |
| Predicate | laterLanguageOfTheology |
P35781
|
FINISHED |
| Object | Kannada |
—
|
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: Kannada | Statement: [Brahma Sampradaya, laterLanguageOfTheology, Kannada]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterLanguageOfTheology Context triple: [Brahma Sampradaya, laterLanguageOfTheology, Kannada]
-
A.
languageOfTheology
chosen
Indicates that a specified language is used as the medium for expressing, studying, or conducting theology in relation to a given religious or theological context.
-
B.
theologyExpressedIn
Indicates that a theological idea, doctrine, or perspective is articulated, represented, or communicated through a particular medium, work, or expression.
-
C.
theologicalField
Indicates that something pertains to or is categorized within a specific area or branch of theology.
-
D.
languageOfReligion
Indicates the language in which a particular religion is traditionally expressed, practiced, or documented.
-
E.
typeOfTheology
Indicates the specific theological category, tradition, or system that characterizes a given religious belief, doctrine, or discourse.
- 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_69ee5bc2b2948190b458ad3f580af779 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f71996e1a48190ac59a1d66d7c44e8 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71820c6c88190ab38b4fa626d22cc |
completed | May 3, 2026, 9:40 a.m. |
Created at: April 26, 2026, 8:11 p.m.