Triple
T24376155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Komatipoort |
E614479
|
entity |
| Predicate | borderPostWith |
P39988
|
FINISHED |
| Object | Ressano Garcia |
—
|
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: Ressano Garcia | Statement: [Komatipoort, borderPostWith, Ressano Garcia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderPostWith Context triple: [Komatipoort, borderPostWith, Ressano Garcia]
-
A.
borderPostIs
Indicates that one entity functions as a border post associated with or located at another entity.
-
B.
borderPostType
Indicates the specific kind or classification of a border post associated with a boundary or crossing point.
-
C.
borderPostName
chosen
Indicates the specific name assigned to a border post where a boundary crossing or checkpoint is located.
-
D.
borderPostHandles
Indicates that a particular border post is responsible for managing, processing, or overseeing a specified type of traffic, activity, or operation.
-
E.
borderStation
Indicates a facility or checkpoint located at or near a border where cross-boundary movement, control, or processing of people or goods occurs.
- 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_69e2d7e1e010819098b95eb3f905943d |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f293d73c0c8190b80e257845a04c57 |
completed | April 29, 2026, 11:27 p.m. |
| PD | Predicate disambiguation | batch_69f287bb1b2c81909c2e7fcc392ad143 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:02 a.m.