Triple
T36662998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Biu–Mandara branch |
E905182
|
entity |
| Predicate | neighboringBranches |
P75455
|
FINISHED |
| Object | Bade–Warji 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: Bade–Warji branch | Statement: [Biu–Mandara branch, neighboringBranches, Bade–Warji branch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: neighboringBranches Context triple: [Biu–Mandara branch, neighboringBranches, Bade–Warji branch]
-
A.
siblingBranch
Indicates that two branches share the same immediate parent node in a hierarchical structure, making them parallel or peer branches.
-
B.
parentBranch
Indicates that one branch serves as the direct ancestor or source from which another branch originates or is derived.
-
C.
neighboringTo
chosen
Indicates that one entity is located directly adjacent or very close to another entity, sharing a common boundary or immediate vicinity.
-
D.
branchesFrom
Indicates that one entity originates or diverges from another as a subordinate or offshoot path, structure, or lineage.
-
E.
neighboringBloc
Indicates that two political or geographic blocs share a common border or are directly adjacent to each other.
- 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_69f76e6e3b908190970251b30f76ad71 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c9f5a8848190ba956ff27f44e396 |
completed | May 3, 2026, 10:19 p.m. |
| PD | Predicate disambiguation | batch_69f7c8999a348190abc1895eaa6e036d |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:12 p.m.