Triple
T22259698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Westerntor |
E550184
|
entity |
| Predicate | hasNameInLanguage |
P15
|
FINISHED |
| Object | Westerntor (German) |
—
|
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: Westerntor (German) | Statement: [Westerntor, hasNameInLanguage, Westerntor (German)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Westerntor (German) Context triple: [Westerntor, hasNameInLanguage, Westerntor (German)]
-
A.
Westerntor
chosen
Westerntor is a historic city gate in Wernigerode, Germany, known as one of the town’s most recognizable medieval landmarks.
-
B.
Schottentor
Schottentor is a historic former city gate area in Vienna that now serves as a major public transport hub and landmark at the edge of the Innere Stadt.
-
C.
Osthofentor
Osthofentor is a historic city gate in Soest, Germany, notable as one of the best-preserved remnants of the town’s medieval fortifications.
-
D.
Nordertor
Nordertor is a historic city gate and one of the best-known architectural symbols of Flensburg, Germany.
-
E.
Tübinger Tor
Tübinger Tor is a historic city gate and notable architectural landmark in Reutlingen, Germany.
- 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_69e11e42adb8819087714772ea606709 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f138c5b54c8190854690ba599639fa |
completed | April 28, 2026, 10:46 p.m. |
Created at: April 16, 2026, 8:39 p.m.