Triple
T28938802
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Special Courts (Sondergerichte) |
E730388
|
entity |
| Predicate | typicalPenalty |
P166927
|
FINISHED |
| Object | long-term imprisonment |
—
|
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: long-term imprisonment | Statement: [Special Courts (Sondergerichte), typicalPenalty, long-term imprisonment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalPenalty Context triple: [Special Courts (Sondergerichte), typicalPenalty, long-term imprisonment]
-
A.
defaultPenalty
Indicates that a standard or automatically applied penalty is imposed in the absence of a specific or overridden penalty.
-
B.
penaltyPoints
Indicates that a certain number of negative points or demerits are assigned to an entity as a consequence of a rule violation, error, or infraction.
-
C.
penaltyTypes
chosen
Indicates the kinds or categories of penalties that are associated with or applied to an entity or action.
-
D.
penaltyRules
Indicates the rules or conditions under which penalties are defined, applied, or enforced in a given context.
-
E.
penaltyResult
Indicates the outcome or consequence that results from a penalty being applied.
- 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_69f043ea0aa88190a25acbf46157995a |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_6a013e23698c81909a32d371b6f158d0 |
completed | May 11, 2026, 2:25 a.m. |
| PD | Predicate disambiguation | batch_6a013db04b108190985897aa6e95b4ec |
completed | May 11, 2026, 2:23 a.m. |
Created at: April 28, 2026, 8:34 a.m.