Triple
T2518482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EK |
E55467
|
entity |
| Predicate | hasNameInGerman |
P22792
|
FINISHED |
| Object |
Erste Kammer
Erste Kammer is the German term for a country's first or upper legislative chamber in a bicameral parliamentary system.
|
E274461
|
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: Erste Kammer | Statement: [EK, hasNameInGerman, Erste Kammer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Erste Kammer Context triple: [EK, hasNameInGerman, Erste Kammer]
-
A.
Grand Bench
The Grand Bench is the full, 15-justice sitting of the Supreme Court of Japan that handles constitutional and other most significant legal cases.
-
B.
Tribunal fédéral
Tribunal fédéral is the French name for the Federal Supreme Court of Switzerland, the country’s highest judicial authority and final court of appeal.
-
C.
Corte
Corte is a historic inland town in central Corsica known for its dramatic citadel and role as a former capital of the island.
-
D.
Second Court
Second Court is one of the main historic courtyards of Jesus College, Cambridge, around which several of the college’s key buildings are arranged.
-
E.
Second Court
Second Court is one of the historic quadrangles of St John’s College, Cambridge, known for its traditional collegiate architecture and central role in college life.
- 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: Erste Kammer Triple: [EK, hasNameInGerman, Erste Kammer]
Generated description
Erste Kammer is the German term for a country's first or upper legislative chamber in a bicameral parliamentary system.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Erste Kammer Target entity description: Erste Kammer is the German term for a country's first or upper legislative chamber in a bicameral parliamentary system.
-
A.
Grand Bench
The Grand Bench is the full, 15-justice sitting of the Supreme Court of Japan that handles constitutional and other most significant legal cases.
-
B.
Tribunal fédéral
Tribunal fédéral is the French name for the Federal Supreme Court of Switzerland, the country’s highest judicial authority and final court of appeal.
-
C.
Corte
Corte is a historic inland town in central Corsica known for its dramatic citadel and role as a former capital of the island.
-
D.
Second Court
Second Court is one of the historic quadrangles of St John’s College, Cambridge, known for its traditional collegiate architecture and central role in college life.
-
E.
Second Court
Second Court is one of the main historic courtyards of Jesus College, Cambridge, around which several of the college’s key buildings are arranged.
- 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_69ab49e4749c8190813311efd1630f1b |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd232ae188190b7b70806b466ee99 |
completed | March 7, 2026, 7:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af2b9ef8048190bafff3f1853321cb |
completed | March 9, 2026, 8:20 p.m. |
| NEDg | Description generation | batch_69af4e240bbc8190bc2392498e3a6be8 |
completed | March 9, 2026, 10:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69af4e816174819095ab81c3902756d6 |
completed | March 9, 2026, 10:49 p.m. |
Created at: March 6, 2026, 9:46 p.m.