Triple
T26186616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Korea |
E654845
|
entity |
| Predicate | capitalCityLocatedOnRiver |
P23341
|
FINISHED |
| Object | Taedong River |
—
|
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: Taedong River | Statement: [North Korea, capitalCityLocatedOnRiver, Taedong River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capitalCityLocatedOnRiver Context triple: [North Korea, capitalCityLocatedOnRiver, Taedong River]
-
A.
capitalCityOnRiver
chosen
Indicates that a capital city is located on and directly adjacent to a particular river.
-
B.
hasCityOnRiver
Indicates that a city is located on or along the course of a particular river.
-
C.
hasMajorCityOnRiver
Indicates that a major city is located on and directly associated with a particular river.
-
D.
largestCityLocatedOnRiver
Indicates that a city is the largest (by population or size) among all cities situated on a given river.
-
E.
capitalCityLocatedOn
Indicates that a capital city is situated on or directly adjacent to a specific geographic feature, such as a river, coast, or lake.
- 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_69ee5b469bc081908fe486453fdad810 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651a731508190bb0c8c2462eba224 |
completed | May 2, 2026, 7:33 p.m. |
Created at: April 26, 2026, 8:42 p.m.