Triple
T21538409
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taebaek, Gangwon Province |
E531412
|
entity |
| Predicate | isWatershedAreaFor |
P17416
|
FINISHED |
| Object | major Korean river systems |
—
|
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: major Korean river systems | Statement: [Taebaek, Gangwon Province, isWatershedAreaFor, major Korean river systems]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isWatershedAreaFor Context triple: [Taebaek, Gangwon Province, isWatershedAreaFor, major Korean river systems]
-
A.
hasWatershed
chosen
Indicates that one geographic area or feature is part of, drains into, or is hydrologically defined by a particular watershed.
-
B.
hasWatershedWith
Indicates that two geographic areas share or are associated with the same watershed or drainage basin.
-
C.
watershedArea
Indicates the total land area from which surface water drains into a particular water body or point in the drainage system.
-
D.
hasWatershedCenter
Indicates that a geographic area or hydrological feature has a designated central point or focal location representing its watershed.
-
E.
hasWatershedCharacteristic
Indicates that a watershed possesses a specified characteristic, feature, or property.
- 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_69e0c45e5b8881908ac18fc2f493b114 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee9d0fdf448190b47ac7c28904f86b |
completed | April 26, 2026, 11:17 p.m. |
| PD | Predicate disambiguation | batch_69e6320766308190ba5dca2f7c826aa4 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:27 p.m.