Triple
T16050727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U-Bahn line U9 |
E389344
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object | Westhafen |
E610258
|
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: Westhafen | Statement: [U-Bahn line U9, hasStation, Westhafen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Westhafen Context triple: [U-Bahn line U9, hasStation, Westhafen]
-
A.
Westhafen
chosen
Westhafen is a major inland port and freight hub in Berlin, serving as one of the city’s key logistics and transportation centers.
-
B.
Gstadt harbor
Gstadt harbor is a lakeside port and departure point on the shores of Lake Chiemsee in Bavaria, Germany, serving as a gateway to the lake’s islands and surrounding attractions.
-
C.
Ostuferhafen
Ostuferhafen is a major ferry and cargo terminal in Kiel, Germany, serving Baltic Sea routes and handling both passenger and freight traffic.
-
D.
Heiligenhafen
Heiligenhafen is a coastal town in northern Germany on the Baltic Sea, known for its fishing harbor, beaches, and tourism.
-
E.
Emder Hafen
Emder Hafen is the historic seaport of the city of Emden in northwestern Germany, serving as an important maritime and commercial hub on the North Sea coast.
- 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_69d86dae698881908327ef2d67706cb9 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e18361c31481908b253e8b814ec9f6 |
completed | April 17, 2026, 12:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffdbe095908190ba10399ad6f3b5f8 |
completed | May 10, 2026, 1:14 a.m. |
Created at: April 10, 2026, 4:56 a.m.