Triple
T18072311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bonn Stadtbahn lines |
E432459
|
entity |
| Predicate | mainUndergroundStation |
P28508
|
FINISHED |
| Object | Bonn Hauptbahnhof underground station |
—
|
NE NERFINISHED |
How this triple was built (3 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: Bonn Hauptbahnhof underground station | Statement: [Bonn Stadtbahn lines, mainUndergroundStation, Bonn Hauptbahnhof underground station]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bonn Hauptbahnhof underground station Context triple: [Bonn Stadtbahn lines, mainUndergroundStation, Bonn Hauptbahnhof underground station]
-
A.
Bonn UN Campus station
Bonn UN Campus station is a light rail and train stop in Bonn, Germany, serving the United Nations campus and nearby conference and government facilities.
-
B.
Bonn-Bad Godesberg station
Bonn-Bad Godesberg station is a railway station in the Bad Godesberg district of Bonn, Germany, serving regional and local train services.
-
C.
Bonn-Beuel station
Bonn-Beuel station is a railway station in the Beuel district of Bonn, Germany, serving regional and local train services.
-
D.
Bonn Hauptbahnhof
chosen
Bonn Hauptbahnhof is the central railway station of Bonn, Germany, serving as a key regional and long-distance transport hub with extensive connections across the Rhine-Ruhr area and beyond.
-
E.
Hallesches Tor station
Hallesches Tor station is a major Berlin U-Bahn interchange station in the Kreuzberg district, serving multiple lines and acting as an important hub in the city’s public transport network.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainUndergroundStation Context triple: [Bonn Stadtbahn lines, mainUndergroundStation, Bonn Hauptbahnhof underground station]
-
A.
subwayStation
chosen
Indicates that one entity is a subway station associated with, located in, or serving the other entity.
-
B.
openedAsUndergroundStation
Indicates that an entity began operation specifically as an underground railway/metro station at the time it was opened.
-
C.
hasNearbyUndergroundStationEntrance
Indicates that one entity is located close to an entrance of an underground (subway/metro) station.
-
D.
operatedUnderground
Indicates that an entity conducted its activities or operations beneath the surface of the ground, rather than at or above ground level.
-
E.
hasSubwayStationEntrance
Indicates that one entity serves as an entrance or access point to a subway station associated with another entity.
- 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_69d8b9070cac81909fa9473fb1c3f1c7 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ccef022c81909be41b2c3a3ee68e |
completed | April 19, 2026, 12:39 p.m. |
| PD | Predicate disambiguation | batch_69e3f90c652481908133a73106d78919 |
completed | April 18, 2026, 9:35 p.m. |
Created at: April 10, 2026, 10:26 a.m.