Triple
T22569903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mahakiranti (proposed) |
E558050
|
entity |
| Predicate | includesLanguage |
P2177
|
FINISHED |
| Object | Dumi language |
—
|
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: Dumi language | Statement: [Mahakiranti (proposed), includesLanguage, Dumi language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dumi language Context triple: [Mahakiranti (proposed), includesLanguage, Dumi language]
-
A.
Dumi language
chosen
Dumi language is a Kiranti language of the Sino-Tibetan family spoken by the Dumi people in eastern Nepal.
-
B.
Buduma language
The Buduma language is an Afro-Asiatic language spoken by the Buduma (Yedina) people around Lake Chad, particularly in Chad and Cameroon.
-
C.
Duruma language
The Duruma language is a Bantu language spoken by the Duruma, one of the Mijikenda peoples of coastal Kenya.
-
D.
Khumi language
The Khumi language is a lesser-known Tibeto-Burman language spoken primarily by the Khumi people in parts of Myanmar and neighboring regions.
-
E.
Medumba language
Medumba is a Bantu-related Grassfields language spoken primarily by the Bamileke people in western Cameroon.
- 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_69e11e5ae4ac8190b1f503457603d969 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15fad35448190b51a3dd639ca8568 |
completed | April 29, 2026, 1:32 a.m. |
Created at: April 16, 2026, 8:52 p.m.