Triple
T1540444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Görlitz |
E32852
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object |
Dicker Turm
Dicker Turm is a historic medieval defensive tower and prominent architectural landmark in the German city of Görlitz.
|
E176716
|
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: Dicker Turm | Statement: [Görlitz, hasLandmark, Dicker Turm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dicker Turm Context triple: [Görlitz, hasLandmark, Dicker Turm]
-
A.
Roter Turm
Roter Turm is a historic medieval tower and prominent architectural landmark in the city center of Chemnitz, Germany.
-
B.
Sauvabelin Tower
Sauvabelin Tower is a wooden observation tower in Lausanne, Switzerland, known for its panoramic views over the city, Lake Geneva, and the surrounding Alps.
-
C.
Hıdırlık Tower
Hıdırlık Tower is an ancient Roman-era stone tower and prominent coastal landmark overlooking the harbor in Antalya, Turkey.
-
D.
Belvedere Tower
Belvedere Tower is a historic ornamental tower located within the grounds of Osborne House, Queen Victoria’s former royal residence on the Isle of Wight.
-
E.
Bower’s Tower
Bower’s Tower is a historic stone watchtower and popular tourist viewpoint in Ibadan, Nigeria, offering panoramic views of the city.
- 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: Dicker Turm Triple: [Görlitz, hasLandmark, Dicker Turm]
Generated description
Dicker Turm is a historic medieval defensive tower and prominent architectural landmark in the German city of Görlitz.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Dicker Turm Target entity description: Dicker Turm is a historic medieval defensive tower and prominent architectural landmark in the German city of Görlitz.
-
A.
Roter Turm
Roter Turm is a historic medieval tower and prominent architectural landmark in the city center of Chemnitz, Germany.
-
B.
Sauvabelin Tower
Sauvabelin Tower is a wooden observation tower in Lausanne, Switzerland, known for its panoramic views over the city, Lake Geneva, and the surrounding Alps.
-
C.
Hıdırlık Tower
Hıdırlık Tower is an ancient Roman-era stone tower and prominent coastal landmark overlooking the harbor in Antalya, Turkey.
-
D.
Belvedere Tower
Belvedere Tower is a historic ornamental tower located within the grounds of Osborne House, Queen Victoria’s former royal residence on the Isle of Wight.
-
E.
Bower’s Tower
Bower’s Tower is a historic stone watchtower and popular tourist viewpoint in Ibadan, Nigeria, offering panoramic views of the city.
- 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_69a885ed29088190a3c2d5a3d100c16e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a9083c942481909168394b6674d82b |
completed | March 5, 2026, 4:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad30997d408190916f16d31bcc35b4 |
completed | March 8, 2026, 8:17 a.m. |
| NEDg | Description generation | batch_69ad31167b748190bbb73d7369570ada |
completed | March 8, 2026, 8:19 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad31b5ce308190ba34123a4c8b8188 |
completed | March 8, 2026, 8:22 a.m. |
Created at: March 4, 2026, 7:26 p.m.