Triple
T37616246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Central Tumbuka |
E935928
|
entity |
| Predicate | principalVarietyOf |
P143417
|
FINISHED |
| Object | Tumbuka 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: Tumbuka language | Statement: [Central Tumbuka, principalVarietyOf, Tumbuka language]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: principalVarietyOf Context triple: [Central Tumbuka, principalVarietyOf, Tumbuka language]
-
A.
isPrimaryVarietyOf
chosen
Indicates that one variety is the main or principal form of another related variety or entity.
-
B.
primaryVariant
Indicates that one entity is the main or canonical version among multiple related variants of another entity.
-
C.
oneOfPrincipalVarietiesWith
Indicates that one entity is among the primary or principal varieties or types associated with another entity.
-
D.
parentVariety
Indicates that one variety is the direct parent or source variety from which another variety is derived or developed.
-
E.
primaryType
Indicates the main or most fundamental category or classification assigned to an entity, distinguishing it from any secondary or auxiliary types.
- F. None of above.
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_69f76ed16b748190ad6add183b1be688 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:18 p.m.