Triple
T21513341
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U8 |
E530781
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object | Kottbusser Tor |
—
|
NE NERFINISHED |
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: Kottbusser Tor | Statement: [U8, hasStation, Kottbusser Tor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kottbusser Tor Context triple: [U8, hasStation, Kottbusser Tor]
-
A.
Kottbusser Tor
chosen
Kottbusser Tor is a major public square and busy U-Bahn interchange station in Berlin’s Kreuzberg district, known for its multicultural atmosphere and dense urban surroundings.
-
B.
Kröpeliner Tor
Kröpeliner Tor is a historic medieval city gate and prominent architectural landmark in the German city of Rostock.
-
C.
Friedländer Tor
Friedländer Tor is a historic brick Gothic city gate in Neubrandenburg, Germany, renowned as part of the town’s well-preserved medieval fortifications.
-
D.
Spandauer Tor
Spandauer Tor was a historic city gate of Berlin that marked the entrance to the city on the road leading toward Spandau.
-
E.
Laufer Tor
Laufer Tor is a historic city gate in Nuremberg’s old town, notable as part of the city’s medieval fortifications.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c45c81f08190a6b8bbb70a45aae7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea88e6fc8190a4b73b8d32dae5a8 |
completed | April 23, 2026, 9:46 a.m. |
Created at: April 16, 2026, 6:25 p.m.