Triple
T19409977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kandh language |
E485561
|
entity |
| Predicate | glottologName |
P6521
|
FINISHED |
| Object | Kandh |
—
|
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: Kandh | Statement: [Kandh language, glottologName, Kandh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kandh Context triple: [Kandh language, glottologName, Kandh]
-
A.
Kandha
chosen
The Kandha are an indigenous tribal community of eastern India, primarily in Odisha, known for their distinct language, traditional agrarian lifestyle, and rich ritual and festival practices.
-
B.
Kanhangad
Kanhangad is a coastal town in the Indian state of Kerala known for its temples, beaches, and proximity to the Bekal Fort area.
-
C.
Kundarki
Kundarki is a notable town in the Moradabad district of Uttar Pradesh, India, serving as a local hub for trade and administration.
-
D.
Kanheya
Kanheya is the surname of Jai Singh Kanheya, associated with a historical family or lineage.
-
E.
Kotagiri
Kotagiri is a hill station town in the Nilgiri district of Tamil Nadu, India, known for its cool climate, tea plantations, and scenic mountain landscapes.
- 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_69d8e8d5162481909db12435d9535c1a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e62af3eaa081909e9537a2c57dc6c1 |
completed | April 20, 2026, 1:32 p.m. |
Created at: April 10, 2026, 1:37 p.m.