Triple
T34433942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drachenfels |
E883899
|
entity |
| Predicate | hasNearbyRiverKilometer |
P56863
|
FINISHED |
| Object | Rhine river kilometer section near Bonn |
—
|
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: Rhine river kilometer section near Bonn | Statement: [Drachenfels, hasNearbyRiverKilometer, Rhine river kilometer section near Bonn]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyRiverKilometer Context triple: [Drachenfels, hasNearbyRiverKilometer, Rhine river kilometer section near Bonn]
-
A.
distanceToMajorRiver
Indicates the measured distance between a given location or entity and the nearest major river.
-
B.
riverTypeNearby
Indicates that one entity is located near a river of a specified type or classification.
-
C.
hasApproxLengthAlongRiver
Indicates that an entity has an approximate measured length that follows the course of a river rather than a straight-line distance.
-
D.
hasNearbyRiverStructure
Indicates that a river-related structure (such as a dam, bridge, or levee) is located close to the referenced entity.
-
E.
riverKilometerContext
chosen
Indicates the position or context of something along a river, measured in river kilometers from a defined reference point.
- 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_69f349c3dd2c819092cc9e64809f4a42 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ffc516d1908190b475f5a6156b0ca8 |
completed | May 9, 2026, 11:36 p.m. |
| PD | Predicate disambiguation | batch_69ffc4a946e08190b3535a5dc15ac484 |
completed | May 9, 2026, 11:35 p.m. |
Created at: May 1, 2026, 2 a.m.