Triple
T3593157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Capture of Munich |
E76073
|
entity |
| Predicate | location |
P40
|
FINISHED |
| Object | Bavaria |
E7752
|
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: Bavaria | Statement: [Capture of Munich, location, Bavaria]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bavaria Context triple: [Capture of Munich, location, Bavaria]
-
A.
Bavaria
chosen
Bavaria is a historic region and federal state in southeastern Germany, known for its distinct cultural traditions, large size and population, and major cities such as Munich.
-
B.
Swabia (Bavaria)
Swabia (Bavaria) is an administrative region in southwestern Bavaria, Germany, known for its distinct Swabian cultural heritage and mix of industrial cities and rural landscapes.
-
C.
Saxony
Saxony is a historic region and former kingdom in eastern Germany, known for its cultural centers like Dresden and Leipzig and its significant role in Central European history.
-
D.
Pfalz
Pfalz is a major wine-producing region in southwestern Germany known for its diverse vineyards and high-quality white wines.
-
E.
Saarland
Saarland is a small federal state in southwestern Germany known for its industrial history, Franco-German cultural influences, and location along the borders with France and Luxembourg.
- 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_69ad85d8042081908af94a04c410dec0 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc15bbbcc81908d6cf95f8e70c6ca |
completed | March 8, 2026, 6:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5b7446bf88190848eb7ecb0e067bd |
completed | March 14, 2026, 7:30 p.m. |
Created at: March 8, 2026, 3:22 p.m.