Triple
T20849503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | B 3 |
E513317
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object |
Marburg
Marburg is a historic university town in the German state of Hesse, known for its well-preserved medieval old town and the Philipps-Universität Marburg.
|
E174796
|
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: Marburg | Statement: [B 3, connects, Marburg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marburg Context triple: [B 3, connects, Marburg]
-
A.
Marburg
Marburg is a historic university town in central Germany known for its well-preserved medieval old town and the Philipps-Universität, one of the oldest Protestant universities in the world.
-
B.
Marburg
Marburg is a small rural township in Queensland, Australia, known for its historic buildings and location between Ipswich and Toowoomba.
-
C.
Diemelstadt
Diemelstadt is a small town in the German state of North Rhine-Westphalia, known for its rural character and location near the Diemel River.
-
D.
Vienenburg
Vienenburg is a district of Goslar in Lower Saxony, Germany, known for its historic town center and proximity to the Harz Mountains.
-
E.
Riemst
Riemst is a municipality in the Belgian province of Limburg, known for its rural character and location near the borders with the Netherlands and 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: Marburg Triple: [B 3, connects, Marburg]
Generated description
Marburg is a historic university town in the German state of Hesse, known for its well-preserved medieval old town and the Philipps-Universität Marburg.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marburg Target entity description: Marburg is a historic university town in the German state of Hesse, known for its well-preserved medieval old town and the Philipps-Universität Marburg.
-
A.
Marburg
chosen
Marburg is a historic university town in central Germany known for its well-preserved medieval old town and the Philipps-Universität, one of the oldest Protestant universities in the world.
-
B.
Marburg
Marburg is a small rural township in Queensland, Australia, known for its historic buildings and location between Ipswich and Toowoomba.
-
C.
Diemelstadt
Diemelstadt is a small town in the German state of North Rhine-Westphalia, known for its rural character and location near the Diemel River.
-
D.
Vienenburg
Vienenburg is a district of Goslar in Lower Saxony, Germany, known for its historic town center and proximity to the Harz Mountains.
-
E.
Riemst
Riemst is a municipality in the Belgian province of Limburg, known for its rural character and location near the borders with the Netherlands and Germany.
- F. None of above.
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_69e0b4f4898081908209e58edb8f9c45 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c3520b0081908ce0f43e8f20b24c |
completed | April 21, 2026, 12:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a090b05d48c8190a394feb0f0add9cf |
completed | May 17, 2026, 12:25 a.m. |
| NEDg | Description generation | batch_6a090bf30e048190a2c81dece02c997d |
completed | May 17, 2026, 12:29 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a090d0d52fc8190aed0a475f3424213 |
completed | May 17, 2026, 12:34 a.m. |
Created at: April 16, 2026, 12:43 p.m.