Triple
T34028835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Talodi languages |
E872585
|
entity |
| Predicate | typologicalAffiliation |
P5201
|
FINISHED |
| Object | Niger–Congo |
—
|
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: Niger–Congo | Statement: [Talodi languages, typologicalAffiliation, Niger–Congo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typologicalAffiliation Context triple: [Talodi languages, typologicalAffiliation, Niger–Congo]
-
A.
typologicalGroup
Indicates that entities are classified together based on shared structural or typological characteristics.
-
B.
languageFamilyAssociation
Indicates an association where one entity belongs to, is classified under, or is related to a particular language family.
-
C.
hasLinguisticTypology
chosen
Indicates a relationship where a language or linguistic system is characterized by a specific typological classification or structural type.
-
D.
inLanguageFamily
Indicates that two languages belong to the same linguistic family or classification.
-
E.
languageFamilyBranchOf
Indicates that one language family branch is a sub-group or subdivision within a larger language family.
- 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_69f349a2527c81909a7cd4bda94d70ad |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f70fb4f18c819099ef6d9177b7d205 |
completed | May 3, 2026, 9:04 a.m. |
| PD | Predicate disambiguation | batch_69f70f3a54d481909ba6bdda3647b761 |
completed | May 3, 2026, 9:02 a.m. |
Created at: May 1, 2026, 1:51 a.m.