Triple
T5980101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pyongyang Metro |
E133097
|
entity |
| Predicate | accessPolicyForForeigners |
P53204
|
FINISHED |
| Object | restricted |
—
|
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: restricted | Statement: [Pyongyang Metro, accessPolicyForForeigners, restricted]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: accessPolicyForForeigners Context triple: [Pyongyang Metro, accessPolicyForForeigners, restricted]
-
A.
shareVisaPolicy
Indicates that two entities apply the same or highly similar visa requirements and entry rules to travelers.
-
B.
foreignPolicyProgram
Indicates a program or initiative that defines, guides, or implements a state's foreign policy toward other international actors.
-
C.
restrictedImmigrantsFrom
Indicates that one entity imposed limitations or prohibitions on immigrants originating from another entity.
-
D.
hasTourismRestriction
chosen
Indicates that there is a limitation, prohibition, or special condition affecting tourism-related activities or access in relation to the referenced entity.
-
E.
visaRequirement
Indicates whether one party must obtain a visa in order to enter, stay in, or transit through the territory of another party.
- 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_69c0086f45e8819098f73dd16d45ec9d |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04dc2243c8190bd3488e7b24af985 |
completed | March 22, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69c049dcb3c081908ccc9b4d4b210229 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:04 p.m.