Triple
T3305560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rosenheim |
E69439
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object |
Riedergarten
Riedergarten is a historic public garden and popular green oasis located in the Bavarian city of Rosenheim, Germany.
|
E347160
|
NE FINISHED |
How this triple was built (4 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: Riedergarten | Statement: [Rosenheim, hasLandmark, Riedergarten]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Riedergarten Context triple: [Rosenheim, hasLandmark, Riedergarten]
-
A.
Berggarten
Berggarten is a historic botanical garden in Hanover, Germany, renowned for its diverse plant collections and greenhouses.
-
B.
Lustgarten
Lustgarten is a historic public park and square on Berlin’s Museum Island, long used as a parade ground and gathering place.
-
C.
Kaiserwiese
Kaiserwiese is a large open meadow within Vienna’s Prater park, commonly used for recreation, events, and public gatherings.
-
D.
Trassenheide
Trassenheide is a seaside resort village on the Baltic Sea coast of the island of Usedom in northeastern Germany, known for its beaches and tourism.
-
E.
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.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Riedergarten Triple: [Rosenheim, hasLandmark, Riedergarten]
Generated description
Riedergarten is a historic public garden and popular green oasis located in the Bavarian city of Rosenheim, Germany.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Riedergarten Target entity description: Riedergarten is a historic public garden and popular green oasis located in the Bavarian city of Rosenheim, Germany.
-
A.
Berggarten
Berggarten is a historic botanical garden in Hanover, Germany, renowned for its diverse plant collections and greenhouses.
-
B.
Lustgarten
Lustgarten is a historic public park and square on Berlin’s Museum Island, long used as a parade ground and gathering place.
-
C.
Kaiserwiese
Kaiserwiese is a large open meadow within Vienna’s Prater park, commonly used for recreation, events, and public gatherings.
-
D.
Trassenheide
Trassenheide is a seaside resort village on the Baltic Sea coast of the island of Usedom in northeastern Germany, known for its beaches and tourism.
-
E.
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.
- F. None of above. chosen
Provenance (5 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_69ad859f218081909458d2cebbf57565 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb0c9470881908c36c1984fdbb67b |
completed | March 8, 2026, 5:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2f3e6e55881909417d54e0d8f0a26 |
completed | March 12, 2026, 5:12 p.m. |
| NEDg | Description generation | batch_69b2fa93ebc0819084c4cdfdb8d6e48d |
completed | March 12, 2026, 5:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b312b6e224819080957998acbed524 |
completed | March 12, 2026, 7:23 p.m. |
Created at: March 8, 2026, 3:11 p.m.