Triple
T1517651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karbi people |
E32156
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Karbi language |
E141283
|
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: Karbi language | Statement: [Karbi people, language, Karbi language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karbi language Context triple: [Karbi people, language, Karbi language]
-
A.
Karbi language
chosen
The Karbi language is a Tibeto-Burman language spoken primarily by the Karbi people in Northeast India, especially in Assam.
-
B.
Kavalan language
The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
-
C.
Kayeli language
The Kayeli language is an Austronesian language once spoken on Buru Island in Indonesia, now critically endangered or possibly extinct.
-
D.
Kaxabu language
The Kaxabu language is an indigenous Formosan language of Taiwan spoken by the Kaxabu people and considered highly endangered.
-
E.
Kalanguya language
The Kalanguya language is an Austronesian language spoken by the Kalanguya people in the northern Luzon highlands of the Philippines.
- 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_69a885e8caf88190a5fbb6159ce87786 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a907eb7d108190bf26199744d510d7 |
completed | March 5, 2026, 4:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad2344f8d8819082e1ae5c980d0525 |
completed | March 8, 2026, 7:20 a.m. |
Created at: March 4, 2026, 7:26 p.m.