Triple
T27946793
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeseníky Mountains foothills |
E700903
|
entity |
| Predicate | formsLowerElevationsOf |
P48833
|
FINISHED |
| Object | Jeseníky mountain system |
—
|
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: Jeseníky mountain system | Statement: [Jeseníky Mountains foothills, formsLowerElevationsOf, Jeseníky mountain system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formsLowerElevationsOf Context triple: [Jeseníky Mountains foothills, formsLowerElevationsOf, Jeseníky mountain system]
-
A.
elevationLowerThan
Indicates that the elevation of one entity is lower than the elevation of another entity.
-
B.
lowerLocation
chosen
Indicates that one entity is located physically below or at a lower vertical position relative to another entity.
-
C.
isLowland
Indicates that an entity is located in, associated with, or characteristic of lowland areas or low-lying terrain relative to surrounding regions.
-
D.
elevationMinApprox
Indicates an approximate value for the minimum elevation associated with an entity or location.
-
E.
elevationMinFeet
Indicates the minimum elevation of an entity or location, measured in feet.
- 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_69ef6a5028108190a14696d9821dde49 |
completed | April 27, 2026, 1:53 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 27, 2026, 7:22 p.m.