Triple
T14005608
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oreshek |
E336938
|
entity |
| Predicate | controlledWaterway |
P68423
|
FINISHED |
| Object | route between Lake Ladoga and Baltic Sea |
—
|
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: route between Lake Ladoga and Baltic Sea | Statement: [Oreshek, controlledWaterway, route between Lake Ladoga and Baltic Sea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: controlledWaterway Context triple: [Oreshek, controlledWaterway, route between Lake Ladoga and Baltic Sea]
-
A.
watercourseControlled
chosen
Indicates that one entity exercises control, regulation, or management over a watercourse (such as a river, stream, or canal).
-
B.
usedWaterway
Indicates that one entity traveled, transported goods, or otherwise moved via a particular waterway as the route or medium of use.
-
C.
stateWaterway
Indicates that a waterway is located within, passes through, or is otherwise geographically associated with a particular state.
-
D.
parallelWaterway
Indicates that one waterway runs alongside another waterway in a roughly parallel course without significantly intersecting it.
-
E.
waterwayClass
Indicates the classification or type of a waterway based on its navigational, functional, or physical characteristics.
- 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_69d81c645c5c8190b1fd16a285a1b78a |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2ed327d88190a53af5768468a8eb |
completed | April 14, 2026, 12:10 p.m. |
| PD | Predicate disambiguation | batch_69dd465dfbc4819090d8c61fd572d35f |
completed | April 13, 2026, 7:39 p.m. |
Created at: April 9, 2026, 10:19 p.m.