Triple
T10441210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Plön |
E246173
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object |
Parnaßturm
Parnaßturm is a historic observation tower in the town of Plön in northern Germany, offering panoramic views over the surrounding lake and countryside landscape.
|
E863122
|
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: Parnaßturm | Statement: [Plön, hasLandmark, Parnaßturm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Parnaßturm Context triple: [Plön, hasLandmark, Parnaßturm]
-
A.
Roter Turm
Roter Turm is a historic medieval tower and prominent architectural landmark in the city center of Chemnitz, Germany.
-
B.
Roter Turm
Roter Turm is a historic clock and bell tower in Halle (Saale), Germany, and one of the city’s most recognizable architectural landmarks.
-
C.
Kollhoff Tower
Kollhoff Tower is a prominent high-rise office building in Berlin known for its brick-clad postmodern architecture and panoramic viewing platform overlooking Potsdamer Platz.
-
D.
Ledererturm
Ledererturm is a historic medieval tower and notable architectural landmark located in the Austrian city of Wels.
-
E.
Jahrtausendturm
The Jahrtausendturm is a distinctive wooden science and technology exhibition tower in Magdeburg, Germany, showcasing the history of human knowledge over the past thousand years.
- 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: Parnaßturm Triple: [Plön, hasLandmark, Parnaßturm]
Generated description
Parnaßturm is a historic observation tower in the town of Plön in northern Germany, offering panoramic views over the surrounding lake and countryside landscape.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Parnaßturm Target entity description: Parnaßturm is a historic observation tower in the town of Plön in northern Germany, offering panoramic views over the surrounding lake and countryside landscape.
-
A.
Roter Turm
Roter Turm is a historic medieval tower and prominent architectural landmark in the city center of Chemnitz, Germany.
-
B.
Roter Turm
Roter Turm is a historic clock and bell tower in Halle (Saale), Germany, and one of the city’s most recognizable architectural landmarks.
-
C.
Kollhoff Tower
Kollhoff Tower is a prominent high-rise office building in Berlin known for its brick-clad postmodern architecture and panoramic viewing platform overlooking Potsdamer Platz.
-
D.
Ledererturm
Ledererturm is a historic medieval tower and notable architectural landmark located in the Austrian city of Wels.
-
E.
Jahrtausendturm
The Jahrtausendturm is a distinctive wooden science and technology exhibition tower in Magdeburg, Germany, showcasing the history of human knowledge over the past thousand years.
- 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_69d381c04fe08190957c26c526a3b05a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4fb9df6fc8190830f405ef955d64b |
completed | April 7, 2026, 12:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d87ed6edd88190afd5063daba58a46 |
completed | April 10, 2026, 4:38 a.m. |
| NEDg | Description generation | batch_69d8837f98e08190bbffa535f94daf48 |
completed | April 10, 2026, 4:58 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d889d0e70c8190953d164f34f01e47 |
completed | April 10, 2026, 5:25 a.m. |
Created at: April 6, 2026, 12:15 p.m.