Triple
T38546574
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bhokar |
E924979
|
entity |
| Predicate | fallsUnderRevenueDivision |
P52313
|
FINISHED |
| Object | Nanded division |
—
|
NE NERFINISHED |
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: Nanded division | Statement: [Bhokar, fallsUnderRevenueDivision, Nanded division]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fallsUnderRevenueDivision Context triple: [Bhokar, fallsUnderRevenueDivision, Nanded division]
-
A.
revenueDivision
Indicates how total revenue is allocated or split among different parties or components.
-
B.
fallsUnderPart
Indicates that one entity is categorized as a specific part or component within a broader entity or grouping.
-
C.
isPartOfDivision
chosen
Indicates that one entity belongs to, or is contained within, a specific division of a larger organizational or structural unit.
-
D.
isMainDivisionOf
Indicates that one division functions as the primary or central division within, or in relation to, another organizational structure.
-
E.
containsDivision
Indicates that one entity includes or encompasses a subdivision or internal division of 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_69f76eadeac081909cdfdd0474cb6765 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcd2ef0e3c8190bac242675003ade6 |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f81cbc8190b4fd3bfc3106c1f3 |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:32 p.m.