Triple
T15067774
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karnali Province |
E379797
|
entity |
| Predicate | hasEthnicGroup |
P1898
|
FINISHED |
| Object | Tamang |
E237477
|
NE FINISHED |
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: Tamang | Statement: [Karnali Province, hasEthnicGroup, Tamang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tamang Context triple: [Karnali Province, hasEthnicGroup, Tamang]
-
A.
Tamang
chosen
Tamang is a Sino-Tibetan language spoken primarily by the Tamang people of Nepal and the Nepali diaspora, including Nepali Americans.
-
B.
Luimbi
Luimbi is a Bantu language spoken in parts of Angola, associated with the Zone L group in the Guthrie classification.
-
C.
Dasu
Dasu is a town in Pakistan that serves as the administrative headquarters of Upper Kohistan District in the Hazara region of Khyber Pakhtunkhwa.
-
D.
Tusita
Tusita is a heavenly realm in Buddhist cosmology where future Buddhas, including Maitreya, reside before their final rebirth.
-
E.
Kangtega
Kangtega is a prominent Himalayan peak in Nepal’s Khumbu region, known for its distinctive saddle-shaped summit and challenging climbing routes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85cd7683881908d405c1b5d7b4f7f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dedeebc7e48190a86b4f0afe8844bb |
completed | April 15, 2026, 12:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fea5cb04e88190a42bb0e516df61bc |
completed | May 9, 2026, 3:11 a.m. |
Created at: April 10, 2026, 3:02 a.m.