Triple
T5543397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unter den Linden |
E145347
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Brandenburg Gate |
E16265
|
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: Brandenburg Gate | Statement: [Unter den Linden, connects, Brandenburg Gate]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brandenburg Gate Context triple: [Unter den Linden, connects, Brandenburg Gate]
-
A.
Brandenburg Gate
chosen
The Brandenburg Gate is an iconic 18th-century monument in Berlin and one of Germany’s most recognizable symbols of history and national unity.
-
B.
Brandenburg Gate (Potsdam)
The Brandenburg Gate in Potsdam is a historic triumphal arch built in the 18th century that serves as one of the city's most prominent architectural landmarks.
-
C.
Berliner Tor
Berliner Tor is a historic city gate in Wesel, Germany, notable for its baroque architecture and role in the town’s former fortifications.
-
D.
Sandauer Tor
Sandauer Tor is a historic city gate in Landsberg am Lech, Germany, forming part of the town’s preserved medieval fortifications.
-
E.
Oranienburger Tor
Oranienburger Tor is an underground station on Berlin’s U-Bahn network located near the historic Oranienburger Tor area in the central district of Mitte.
- 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_69c008fa64888190adae56c8f9ea4031 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01fc947bc81908d1f7b709392ec20 |
completed | March 22, 2026, 4:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c02822fb80819087474c37d6dc4d2b |
completed | March 22, 2026, 5:34 p.m. |
Created at: March 22, 2026, 3:35 p.m.