Triple
T14754950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1. Bezirk |
E346706
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Am Hof |
E346728
|
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: Am Hof | Statement: [1. Bezirk, hasLandmark, Am Hof]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Am Hof Context triple: [1. Bezirk, hasLandmark, Am Hof]
-
A.
Am Hof
chosen
Am Hof is a historic square in Vienna’s Innere Stadt district, known for its medieval origins, notable architecture, and role as a former center of civic and religious life.
-
B.
Haus am Horn
Haus am Horn is a pioneering early Bauhaus model house in Weimar, Germany, designed in 1923 to showcase modernist architecture and functional living.
-
C.
Wellblechpalast
Wellblechpalast is an ice hockey arena in Berlin best known as the longtime home of the Eisbären Berlin before their move to larger, modern venues.
-
D.
Königswinter
Königswinter is a town on the right bank of the Rhine in North Rhine-Westphalia, Germany, known for the Drachenfels hill and its scenic location in the Siebengebirge range.
-
E.
Das Schloss
Das Schloss is a prominent shopping mall in Berlin known for its distinctive architecture and wide range of retail and dining options.
- 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_69d822e8896c819091169882f9b20486 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69dec7d59df08190a86da5048358bd6e |
completed | April 14, 2026, 11:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdfb9e1b8481909abea3daabe91302 |
completed | May 8, 2026, 3:05 p.m. |
Created at: April 10, 2026, 1:30 a.m.