Triple
T4981025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Judiciary of Germany |
E111882
|
entity |
| Predicate | hasSpecialCourtType |
P32551
|
FINISHED |
| Object | constitutional court |
—
|
LITERAL FINISHED |
How this triple was built (2 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: constitutional court | Statement: [Judiciary of Germany, hasSpecialCourtType, constitutional court]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpecialCourtType Context triple: [Judiciary of Germany, hasSpecialCourtType, constitutional court]
-
A.
hasSpecialCourts
chosen
Indicates that a legal system or jurisdiction possesses dedicated courts established to handle specific types of cases or legal matters separately from general courts.
-
B.
hasTypeOfCourt
Indicates that an entity is associated with or classified by a specific type or category of court.
-
C.
hasCourts
Indicates that an entity possesses, contains, or is equipped with one or more courts (e.g., legal, sports, or judicial facilities).
-
D.
hasStateCourt
Indicates that a given jurisdiction or region possesses an official court that operates at the state level.
-
E.
recognizesCourt
Indicates that one legal authority formally accepts the legitimacy or jurisdiction of a particular court.
- F. None of above.
Provenance (3 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_69bd441adc208190b70a033a0741d01e |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd730a7590819088ab8d49c5c88c2f |
completed | March 20, 2026, 4:17 p.m. |
| PD | Predicate disambiguation | batch_69bd7146e6e881908a55ab2756b631f6 |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:33 p.m.