Triple
T9540722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kelheim (district) |
E230148
|
entity |
| Predicate | containsTown |
P847
|
FINISHED |
| Object | Abensberg |
E692006
|
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: Abensberg | Statement: [Kelheim (district), containsTown, Abensberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Abensberg Context triple: [Kelheim (district), containsTown, Abensberg]
-
A.
Abensberg
chosen
Abensberg is a historic town in Bavaria, Germany, known for its medieval architecture and its role as a Napoleonic-era battlefield.
-
B.
Wilhelmsruh
Wilhelmsruh is a locality in the borough of Pankow in Berlin, Germany, known for its residential character and historical ties to Berlin’s former border zone.
-
C.
Ansbach
Ansbach is a historic town in the German state of Bavaria, known as the former residence of the Margraves of Brandenburg-Ansbach.
-
D.
Katharinenfeld
Katharinenfeld was the historical German settler colony that later became the town of Bolnisi in southern Georgia.
-
E.
Hildburghausen
Hildburghausen is a town in the German state of Thuringia that historically served as the residence of the dukes of Saxe-Hildburghausen.
- 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_69ca847b1b3081908f72bc932c17cc41 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd98e695948190ab107fff38c57de7 |
completed | April 1, 2026, 10:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2e4fa938881908253aed52870210d |
completed | April 5, 2026, 10:40 p.m. |
Created at: March 30, 2026, 8:01 p.m.