Triple
T3336781
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Limmat |
E70156
|
entity |
| Predicate | hasBridge |
P386
|
FINISHED |
| Object | Kornhausbrücke |
E352212
|
NE 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: Kornhausbrücke | Statement: [Limmat, hasBridge, Kornhausbrücke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kornhausbrücke Context triple: [Limmat, hasBridge, Kornhausbrücke]
-
A.
Schlossbrücke
Schlossbrücke is a historic bridge in central Berlin that spans the Spree River, connecting Unter den Linden with Museum Island near the Berlin Palace.
-
B.
Rathausbrücke
chosen
Rathausbrücke is a historic pedestrian bridge in central Zurich, Switzerland, spanning the Limmat River near the city hall and the old town.
-
C.
Untermainbrücke
Untermainbrücke is a road and pedestrian bridge over the Main River in Frankfurt am Main, Germany, linking the city center with the museum-lined Schaumainkai on the south bank.
-
D.
Hohenzollern Bridge
The Hohenzollern Bridge is a historic railway and pedestrian bridge over the Rhine in Cologne, Germany, famous for its heavy train traffic and thousands of love locks attached to its railings.
-
E.
Hogeweidebrug
Hogeweidebrug is a bridge spanning the Amsterdam–Rhine Canal in the Netherlands, serving as part of the local road and transport infrastructure.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad85a24f208190bcf83131bfed3521 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb1bad97481909359e914d44a1a74 |
completed | March 8, 2026, 5:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b360a07dec819094b0645d0e2a91da |
completed | March 13, 2026, 12:56 a.m. |
Created at: March 8, 2026, 3:12 p.m.