Triple
T7679173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Compiègne |
E173943
|
entity |
| Predicate | twinTown |
P1072
|
FINISHED |
| Object | Landshut |
E302865
|
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: Landshut | Statement: [Compiègne, twinTown, Landshut]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Landshut Context triple: [Compiègne, twinTown, Landshut]
-
A.
Landshut
chosen
Landshut is a historic Bavarian city in southeastern Germany known for its well-preserved medieval architecture and the landmark Trausnitz Castle.
-
B.
Augsburg
Augsburg is one of Germany’s oldest cities, a historic Bavarian center known for its rich Renaissance heritage and role as a major medieval trading hub.
-
C.
Kempten
Kempten is a historic town in Bavaria, Germany, considered one of the country’s oldest urban settlements and known for its location in the Allgäu region.
-
D.
Kaufbeuren
Kaufbeuren is a historic Bavarian town in southern Germany known for its well-preserved medieval old town and traditional Swabian culture.
-
E.
Rosenheim
Rosenheim is a town in Upper Bavaria, Germany, known as a regional economic and transportation hub near the Alps.
- 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_69c6995703e0819081de77361b602e78 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c701fe2cc88190b5fd5e1378c32e5b |
completed | March 27, 2026, 10:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c9c2e6b2e88190be579a15109d4f82 |
completed | March 30, 2026, 12:25 a.m. |
Created at: March 27, 2026, 4:01 p.m.