Triple
T4523664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kauravas |
E103324
|
entity |
| Predicate | languageOfNarrative |
P17914
|
FINISHED |
| Object | Sanskrit |
—
|
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: Sanskrit | Statement: [Kauravas, languageOfNarrative, Sanskrit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfNarrative Context triple: [Kauravas, languageOfNarrative, Sanskrit]
-
A.
languageOfWritings
chosen
Indicates that a specified language is the one in which certain writings or written works are composed.
-
B.
narrativeType
Indicates the specific kind or category of narrative (e.g., genre, structural form, or storytelling mode) associated with an entity.
-
C.
narrative
Indicates that one entity tells, presents, or conveys a story or sequence of events about another entity or situation.
-
D.
narrativeTradition
Indicates the storytelling customs, conventions, or patterns that shape how narratives are typically told within a particular culture, group, or context.
-
E.
narrativeStyle
Indicates how a narrative is told, such as the point of view, tone, and structural approach used to present a story or account.
- 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_69bd43dba59881908cf59b31df8c7ae1 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd574d7c2481909049955ca47613a6 |
completed | March 20, 2026, 2:18 p.m. |
| PD | Predicate disambiguation | batch_69bd521cf77c819083852de3094d1377 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:03 p.m.