Triple
T25473688
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Korean railway network |
E638370
|
entity |
| Predicate | hasBorderConnectionPotential |
P162101
|
FINISHED |
| Object | North Korea |
—
|
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: North Korea | Statement: [South Korean railway network, hasBorderConnectionPotential, North Korea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBorderConnectionPotential Context triple: [South Korean railway network, hasBorderConnectionPotential, North Korea]
-
A.
hasBorderConnection
Indicates that two regions or entities share a common boundary or are directly connected along a border.
-
B.
hasBorderRelation
Indicates that one entity shares a boundary or border with another entity.
-
C.
hasBorderThrough
Indicates that a border between two regions or entities passes through or along a specified intermediate area, feature, or object.
-
D.
hasBorderTerminus
Indicates that one entity serves as the endpoint or terminal location of another entity’s border or boundary.
-
E.
connectsToCountryBorder
Indicates that one entity is directly adjacent to and touches the border of a specified country.
- 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_69e75db9b964819096802dcf502e577e |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f622abdfac8190988421c946411d7e |
completed | May 2, 2026, 4:13 p.m. |
| PD | Predicate disambiguation | batch_69f620dc38088190b56b2b15ed75b3c2 |
completed | May 2, 2026, 4:05 p.m. |
| PDg | Predicate description generation | batch_69f621fbfc2c8190bfa802d7dc0f6aa4 |
completed | May 2, 2026, 4:10 p.m. |
Created at: April 21, 2026, 2:25 p.m.