Triple
T7001944
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Musegg Wall |
E162356
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Heuturm
Heuturm is one of the historic defensive towers incorporated into Lucerne’s medieval Musegg Wall in Switzerland.
|
E634686
|
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: Heuturm | Statement: [Musegg Wall, hasPart, Heuturm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heuturm Context triple: [Musegg Wall, hasPart, Heuturm]
-
A.
Verwoerdburg
Verwoerdburg was the former name of part of the modern South African city of Centurion, historically associated with the apartheid-era figure Hendrik Verwoerd.
-
B.
Kronenburgertoren
Kronenburgertoren is a historic medieval city tower in Nijmegen, Netherlands, known as a prominent remnant of the old city fortifications.
-
C.
Humberg Tower
Humberg Tower is a historic observation tower on the Humberg hill near Kaiserslautern in Germany, known for its panoramic views over the surrounding Palatinate region.
-
D.
Bronckhorst Castle
Bronckhorst Castle is a historic Dutch stronghold that served as the ancestral residence of the noble House of Limburg Stirum.
-
E.
Stuyvenberg Castle
Stuyvenberg Castle is a historic royal residence in Laeken, Brussels, long associated with the Belgian monarchy and used as a home for members of the royal family.
- 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: Heuturm Triple: [Musegg Wall, hasPart, Heuturm]
Generated description
Heuturm is one of the historic defensive towers incorporated into Lucerne’s medieval Musegg Wall in Switzerland.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Heuturm Target entity description: Heuturm is one of the historic defensive towers incorporated into Lucerne’s medieval Musegg Wall in Switzerland.
-
A.
Verwoerdburg
Verwoerdburg was the former name of part of the modern South African city of Centurion, historically associated with the apartheid-era figure Hendrik Verwoerd.
-
B.
Kronenburgertoren
Kronenburgertoren is a historic medieval city tower in Nijmegen, Netherlands, known as a prominent remnant of the old city fortifications.
-
C.
Humberg Tower
Humberg Tower is a historic observation tower on the Humberg hill near Kaiserslautern in Germany, known for its panoramic views over the surrounding Palatinate region.
-
D.
Bronckhorst Castle
Bronckhorst Castle is a historic Dutch stronghold that served as the ancestral residence of the noble House of Limburg Stirum.
-
E.
Stuyvenberg Castle
Stuyvenberg Castle is a historic royal residence in Laeken, Brussels, long associated with the Belgian monarchy and used as a home for members of the royal family.
- 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_69c68857ffc08190857dc62cd5253777 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6dc1115c48190a9363473ae21b6c1 |
completed | March 27, 2026, 7:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c76a310eb08190a0fc1de2814aea08 |
completed | March 28, 2026, 5:42 a.m. |
| NEDg | Description generation | batch_69c76b1d881481908ef5a6614246ca1e |
completed | March 28, 2026, 5:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c76be95ecc8190a57ff197f236d434 |
completed | March 28, 2026, 5:49 a.m. |
Created at: March 27, 2026, 2:33 p.m.