Triple
T23288961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Korea–Russia border |
E589971
|
entity |
| Predicate | hasNoOfficialRoadCrossing |
P58770
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [North Korea–Russia border, hasNoOfficialRoadCrossing, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNoOfficialRoadCrossing Context triple: [North Korea–Russia border, hasNoOfficialRoadCrossing, true]
-
A.
hasNoDirectRoadAccess
chosen
Indicates that there is no direct road connection available between the relevant locations or entities.
-
B.
notCrossing
Indicates that two entities do not intersect, overlap, or pass through each other in space or along their paths.
-
C.
hasRailwayCrossing
Indicates that a location or route includes a point where a railway line and a road or path intersect, typically at the same level.
-
D.
hasNoTrafficSignals
Indicates that along the specified road segment or at the specified location, there are no traffic control signals present or in operation.
-
E.
usesPublicRoads
Indicates that an entity travels on, operates vehicles on, or otherwise makes use of publicly accessible roadways.
- 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_69e25d1af9d88190a0b9b5e8fa608618 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f19649570c8190b565fafa55b1f886 |
completed | April 29, 2026, 5:25 a.m. |
| PD | Predicate disambiguation | batch_69effcf325f88190b320268c3c551abb |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 5:01 p.m.