Triple
T31664944
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pyongan Province |
E808099
|
entity |
| Predicate | territoryNowMostlyIn |
P8402
|
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: [Pyongan Province, territoryNowMostlyIn, North Korea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: territoryNowMostlyIn Context triple: [Pyongan Province, territoryNowMostlyIn, North Korea]
-
A.
currentTerritoryMostlyIn
chosen
Indicates that the majority of the current territorial area of one entity lies within the territorial boundaries of another entity.
-
B.
wasCoreTerritoryOf
Indicates that a region historically formed the central or most important territorial area belonging to a particular political or cultural entity.
-
C.
partOfTerritory
Indicates that one geographic or administrative area is contained within, and forms a constituent portion of, another territory.
-
D.
territoryLaterControlledBy
Indicates that a territory was subsequently governed, ruled, or administered by a specified controlling entity after an earlier period.
-
E.
partlyFormedFromTerritoryOf
Indicates that an entity was created or established using only a portion of the territory of another entity, rather than its entire area.
- 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_69f348dbeef4819080b446a7feb6340b |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 30, 2026, 10:59 p.m.