Triple
T24478300
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Potou languages |
E617292
|
entity |
| Predicate | primaryBranchOf |
P78334
|
FINISHED |
| Object | Potou–Tano languages |
—
|
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: Potou–Tano languages | Statement: [Potou languages, primaryBranchOf, Potou–Tano languages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryBranchOf Context triple: [Potou languages, primaryBranchOf, Potou–Tano languages]
-
A.
centralBranch
Indicates that one entity functions as the main or primary branch within a larger organizational or structural system relative to another entity.
-
B.
parentBranch
Indicates that one branch serves as the direct ancestor or source from which another branch originates or is derived.
-
C.
representedBranch
Indicates that one entity serves as a representative or proxy for a particular branch of another entity or organization.
-
D.
dominantBranch
chosen
Indicates that one branch in a branching structure is the primary or prevailing branch relative to the others.
-
E.
supportingBranch
Indicates that one branch structurally or functionally supports another branch.
- 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_69e2d7f3ae788190b683394db15f220e |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f29ed3fce88190b5be7e085ef88c97 |
completed | April 30, 2026, 12:14 a.m. |
| PD | Predicate disambiguation | batch_69f287d76c7c81909494f12e606a9149 |
completed | April 29, 2026, 10:36 p.m. |
Created at: April 18, 2026, 2:21 a.m.