Triple
T6710889
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Bantu languages |
E153135
|
entity |
| Predicate | hasGlottologClassification |
P33198
|
FINISHED |
| Object | Southern Bantoid branch |
—
|
LITERAL 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: Southern Bantoid branch | Statement: [Southern Bantu languages, hasGlottologClassification, Southern Bantoid branch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGlottologClassification Context triple: [Southern Bantu languages, hasGlottologClassification, Southern Bantoid branch]
-
A.
hasGlottologName
Indicates that an entity is associated with a specific name as recorded in the Glottolog linguistic database.
-
B.
glottocode
Indicates the standardized Glottolog code that uniquely identifies the language or dialect associated with an entity.
-
C.
glottoCategory
chosen
Indicates the linguistic classification or type (such as language family, subgroup, or category) to which a language or dialect is assigned.
-
D.
glottologStatus
Indicates the classification or status of a language or dialect as defined in the Glottolog database.
-
E.
linguisticClassification
Indicates the relationship by which an entity is categorized according to its language or linguistic type.
- 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_69c68808d8d8819087369015270788fe |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d121a92c8190a03f384a8aba84da |
completed | March 27, 2026, 6:49 p.m. |
| PD | Predicate disambiguation | batch_69c6d08c5d348190a29dee668c398e70 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:06 p.m.