Triple
T7274010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dioula |
E162977
|
entity |
| Predicate | hasMacrolanguageRelation |
P23734
|
FINISHED |
| Object | Manding macrolanguage |
—
|
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: Manding macrolanguage | Statement: [Dioula, hasMacrolanguageRelation, Manding macrolanguage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMacrolanguageRelation Context triple: [Dioula, hasMacrolanguageRelation, Manding macrolanguage]
-
A.
macrolanguageMemberOf
Indicates that a language variety is classified as a member of a larger macrolanguage grouping.
-
B.
macrolanguageOf
chosen
Indicates that one language functions as a macrolanguage encompassing or grouping together one or more related individual languages.
-
C.
hasStandardLanguageRelation
Indicates that there exists a standardized linguistic relationship between two entities, such as one being the standard or reference language form for the other.
-
D.
macrolanguage
Indicates that a language is classified as a macrolanguage encompassing multiple closely related individual languages or varieties.
-
E.
ISO639Macrolanguage
Indicates that a language variety is part of a broader ISO 639-defined macrolanguage grouping that encompasses multiple closely related individual languages.
- 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_69c6885c5964819085b209701769877f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eb8a0b4881908ff27c5a75bd4a95 |
completed | March 27, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69c6e76a84a081908d4184c55b728e48 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:58 p.m.