Triple
T10064630
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Braunfels Castle |
E213068
|
entity |
| Predicate | surroundedBy |
P224
|
FINISHED |
| Object |
historic old town of Braunfels
The historic old town of Braunfels is a picturesque medieval German town center characterized by half-timbered houses, narrow cobbled streets, and a hilltop castle dominating its skyline.
|
E838865
|
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: historic old town of Braunfels | Statement: [Braunfels Castle, surroundedBy, historic old town of Braunfels]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: historic old town of Braunfels Context triple: [Braunfels Castle, surroundedBy, historic old town of Braunfels]
-
A.
Burghausen old town
Burghausen old town is a historic Bavarian town renowned for its medieval architecture and its hilltop castle complex, one of the longest castle ensembles in the world.
-
B.
Old Town of Hanau
The Old Town of Hanau is the historic core of the German city of Hanau, characterized by its traditional urban layout, heritage buildings, and central role in the city’s cultural and historical identity.
-
C.
historic town center of Landsberg am Lech
The historic town center of Landsberg am Lech is a well-preserved medieval Bavarian old town on the Lech River, known for its picturesque architecture, city walls, and historic gates.
-
D.
Historic City Centre of Braunschweig
The Historic City Centre of Braunschweig is the medieval core of the German city of Braunschweig, characterized by its historic squares, churches, and preserved architectural ensembles reflecting its past as an important Hanseatic and ducal residence city.
-
E.
historic Old Town
The historic Old Town of Przemyśl is a well-preserved medieval city center in southeastern Poland, known for its picturesque architecture, cobbled streets, and layered multicultural history.
- 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: historic old town of Braunfels Triple: [Braunfels Castle, surroundedBy, historic old town of Braunfels]
Generated description
The historic old town of Braunfels is a picturesque medieval German town center characterized by half-timbered houses, narrow cobbled streets, and a hilltop castle dominating its skyline.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: historic old town of Braunfels Target entity description: The historic old town of Braunfels is a picturesque medieval German town center characterized by half-timbered houses, narrow cobbled streets, and a hilltop castle dominating its skyline.
-
A.
Burghausen old town
Burghausen old town is a historic Bavarian town renowned for its medieval architecture and its hilltop castle complex, one of the longest castle ensembles in the world.
-
B.
Old Town of Hanau
The Old Town of Hanau is the historic core of the German city of Hanau, characterized by its traditional urban layout, heritage buildings, and central role in the city’s cultural and historical identity.
-
C.
historic town center of Landsberg am Lech
The historic town center of Landsberg am Lech is a well-preserved medieval Bavarian old town on the Lech River, known for its picturesque architecture, city walls, and historic gates.
-
D.
Historic City Centre of Braunschweig
The Historic City Centre of Braunschweig is the medieval core of the German city of Braunschweig, characterized by its historic squares, churches, and preserved architectural ensembles reflecting its past as an important Hanseatic and ducal residence city.
-
E.
historic Old Town
The historic Old Town of Przemyśl is a well-preserved medieval city center in southeastern Poland, known for its picturesque architecture, cobbled streets, and layered multicultural history.
- 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_69ca83977128819084084eb7d1d8c52a |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdcfd653748190aeddf7a679028604 |
completed | April 2, 2026, 2:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d29a84c3308190ba9286053c1017dc |
completed | April 5, 2026, 5:23 p.m. |
| NEDg | Description generation | batch_69d29b985e308190a6ec3966e02f429c |
completed | April 5, 2026, 5:27 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d29c5f64c881909aa3d093422fe475 |
completed | April 5, 2026, 5:31 p.m. |
Created at: March 30, 2026, 8:58 p.m.