Triple
T23270849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Western Kalanga |
E588283
|
entity |
| Predicate | subdivisionOf |
P258
|
FINISHED |
| Object | Kalanga 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: Kalanga language | Statement: [Western Kalanga, subdivisionOf, Kalanga language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kalanga language Context triple: [Western Kalanga, subdivisionOf, Kalanga language]
-
A.
Kalanga language
chosen
The Kalanga language is a Bantu language spoken primarily by the Kalanga people in parts of Botswana and southwestern Zimbabwe.
-
B.
Malasanga language
The Malasanga language is an Oceanic language spoken in Papua New Guinea, belonging to the Kula–Malasanga subgroup of the Austronesian language family.
-
C.
Khoe-Kwadi language
Khoe-Kwadi is a proposed language family of southern Africa that groups together the Khoe (Khoikhoi and related) languages with the extinct Kwadi language of Angola.
-
D.
Tembe language
The Tembe language is an indigenous Tupi-Guarani language spoken by the Tembé people of northern Brazil.
-
E.
Teke-Ngungwel language
The Teke-Ngungwel language is a Bantu language spoken by the Teke people in Central Africa, particularly in parts of the Republic of the Congo and neighboring regions.
- 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_69e25d148adc819088efbf42672604e9 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1957418fc819085ee528622e0c6de |
completed | April 29, 2026, 5:21 a.m. |
Created at: April 17, 2026, 4:45 p.m.