Triple
T20587290
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barwani State |
E505818
|
entity |
| Predicate | sharesBorderWith |
P224
|
FINISHED |
| Object | Dhar State |
—
|
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: Dhar State | Statement: [Barwani State, sharesBorderWith, Dhar State]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dhar State Context triple: [Barwani State, sharesBorderWith, Dhar State]
-
A.
Dhar State
chosen
Dhar State was a former princely state in central India, historically ruled by the Pawar (Parmar) Maratha dynasty with its capital at the town of Dhar.
-
B.
Bharana State
Bharana State was a small princely state in colonial India that formed part of the group of minor hill principalities collectively known as the Simla Hill States.
-
C.
Mundhar State
Mundhar State was a small princely hill state located in the Simla Hills region of colonial India.
-
D.
Morvi State
Morvi State was a former princely state in western India, historically governed by the Jadeja Rajput dynasty.
-
E.
Bijawar State
Bijawar State was a former princely state in British India, located in the Bundelkhand region of present-day Madhya Pradesh.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4b9669c8190b8e81fc72817d42c |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a977fb18819085fee5cf5d45c1b0 |
completed | April 20, 2026, 10:32 p.m. |
Created at: April 16, 2026, 11:40 a.m.