Triple
T20419858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nitish Kumar |
E500816
|
entity |
| Predicate | ethnicGroup |
P194
|
FINISHED |
| Object | Kurmi |
—
|
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: Kurmi | Statement: [Nitish Kumar, ethnicGroup, Kurmi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kurmi Context triple: [Nitish Kumar, ethnicGroup, Kurmi]
-
A.
Kurmi
chosen
Kurmi is an agricultural caste community of northern and eastern India, traditionally known as skilled cultivators and landholders.
-
B.
Kamli
"Kamli" is a popular Bollywood song sung by Indian playback singer Sunidhi Chauhan, known for its high energy and powerful vocals.
-
C.
Panchet
Panchet is a town in the eastern Indian state of Jharkhand, known for the Panchet Dam on the Damodar River and its proximity to coal-mining and industrial regions.
-
D.
Karwi
Karwi is a town in Uttar Pradesh, India, known primarily as the rail and road gateway to the historic hill fort of Kalinjar.
-
E.
Cheeni Kum
Cheeni Kum is a 2007 Indian romantic comedy film directed by R. Balki, known for its unconventional love story between an older chef and a much younger woman, played by Tabu.
- 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_69e0b4a935588190b9446a99b37ced44 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67ba39f7081909358f1103a0f241c |
completed | April 20, 2026, 7:16 p.m. |
Created at: April 16, 2026, 11:30 a.m.