Triple
T10797493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gradignan |
E254747
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Pfaffenhofen an der Ilm |
E243687
|
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: Pfaffenhofen an der Ilm | Statement: [Gradignan, hasTwinTown, Pfaffenhofen an der Ilm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pfaffenhofen an der Ilm Context triple: [Gradignan, hasTwinTown, Pfaffenhofen an der Ilm]
-
A.
Pfaffenhofen an der Ilm
chosen
Pfaffenhofen an der Ilm is a Bavarian town in southern Germany known for its historic center, hop-growing tradition, and location between Munich and Ingolstadt.
-
B.
Pfaffenhofen an der Roth
Pfaffenhofen an der Roth is a municipality in the district of Neu-Ulm in the Bavarian region of Germany.
-
C.
Pfeffenhausen
Pfeffenhausen is a market town in Lower Bavaria, Germany, known for its rural character and location within the Landshut district.
-
D.
Zusenhofen
Zusenhofen is a village and district within the town of Oberkirch in the Ortenau region of Baden-Württemberg, Germany.
-
E.
Herzogenaurach
Herzogenaurach is a Bavarian town in Germany best known as the birthplace and headquarters of the global sportswear brands Adidas and Puma.
- 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_69d6aa61c15c8190a1839550c56e75e1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d73333dc4081909faa40c10bce2735 |
completed | April 9, 2026, 5:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69dff7b050ec8190b75877d5724c2aec |
completed | April 15, 2026, 8:40 p.m. |
Created at: April 8, 2026, 9:17 p.m.