Triple
T9498670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neumarkt in der Oberpfalz (district) |
E229077
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Hohenfels (Oberpfalz) |
E625173
|
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: Hohenfels (Oberpfalz) | Statement: [Neumarkt in der Oberpfalz (district), contains, Hohenfels (Oberpfalz)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hohenfels (Oberpfalz) Context triple: [Neumarkt in der Oberpfalz (district), contains, Hohenfels (Oberpfalz)]
-
A.
Hohenfels, Germany
chosen
Hohenfels, Germany is a Bavarian town best known for hosting a major U.S. Army and NATO training area, including the Joint Multinational Readiness Center.
-
B.
Vockenhausen
Vockenhausen is a district of the town of Eppstein in the German state of Hesse.
-
C.
Fürstenfeldbruck
Fürstenfeldbruck is a town in Upper Bavaria, Germany, known for its historic monastery, proximity to Munich, and nearby air base.
-
D.
Fürstenried
Fürstenried is a residential district in the southwest of Munich, Germany, known for its post-war housing estates and proximity to green spaces and the Fürstenried Palace.
-
E.
Fürstenfeldbruck Air Base
Fürstenfeldbruck Air Base is a German military airfield near Munich, historically known as the site of the failed rescue attempt during the 1972 Munich Olympics massacre.
- 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_69ca84753660819098e8d416e89e26ae |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd983a94c48190a7ddf95a953c4ecc |
completed | April 1, 2026, 10:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d12d3aafb88190ac53289039bca88a |
completed | April 4, 2026, 3:24 p.m. |
Created at: March 30, 2026, 7:56 p.m.