Triple
T2025188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Upper Bavaria |
E44191
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Starnberg |
E42787
|
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: Starnberg | Statement: [Upper Bavaria, contains, Starnberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Starnberg Context triple: [Upper Bavaria, contains, Starnberg]
-
A.
Starnberg
chosen
Starnberg is a lakeside town in Bavaria, Germany, known for its affluent residential character and scenic location on Lake Starnberg southwest of Munich.
-
B.
Landsberg
Landsberg is a town in the Saalekreis district of the German state of Saxony-Anhalt.
-
C.
Idstein
Idstein is a historic town in the German state of Hesse, known for its well-preserved medieval old town and timber-framed architecture.
-
D.
Brackenheim
Brackenheim is a small town in the German state of Baden-Württemberg, best known as the birthplace of Theodor Heuss, the first President of the Federal Republic of Germany.
-
E.
Landsberg am Lech
Landsberg am Lech is a historic Bavarian town in southern Germany known for its medieval old town, picturesque setting on the Lech River, and its association with the nearby Landsberg Prison.
- 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_69a8891201bc8190aca837be6de41579 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb8f3faa08190a48ae1355d6e009f |
completed | March 7, 2026, 5:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af5cbcf8dc8190a3319bdf58dce307 |
completed | March 9, 2026, 11:50 p.m. |
Created at: March 4, 2026, 7:38 p.m.