Triple
T27855021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ǁKaras Region |
E704058
|
entity |
| Predicate | borderTypeWithSouthAfrica |
P192702
|
FINISHED |
| Object | river border |
—
|
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: river border | Statement: [ǁKaras Region, borderTypeWithSouthAfrica, river border]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderTypeWithSouthAfrica Context triple: [ǁKaras Region, borderTypeWithSouthAfrica, river border]
-
A.
borderTypeWithKenya
Indicates the type or nature of the border relationship that an entity shares with Kenya.
-
B.
borderTypeWithVenezuela
Indicates the specific type or nature of the border that an entity shares with Venezuela.
-
C.
boundaryTypeSouth
Indicates the type or nature of the boundary that lies to the south of a given entity.
-
D.
borderTypeWithMongolia
Indicates the specific nature or classification of the border that an entity shares with Mongolia.
-
E.
borderTypeToNiger
Indicates the type or nature of the border that an entity shares with Niger.
- F. None of above. chosen
Provenance (4 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_69ef840e614c8190a88cf9638c14a265 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69fd2839880c819099a7a89783f2270e |
completed | May 8, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69fd23dc5da48190ae8ba08947d34956 |
completed | May 7, 2026, 11:44 p.m. |
| PDg | Predicate description generation | batch_69fd28379d2c8190903ba228ee1cc756 |
completed | May 8, 2026, 12:03 a.m. |
Created at: April 27, 2026, 6:13 p.m.