Triple
T34516208
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Radovan Krejcir |
E886157
|
entity |
| Predicate | hasPrisonSentence |
P20881
|
FINISHED |
| Object | long-term imprisonment in South Africa |
—
|
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 in South Africa | Statement: [Radovan Krejcir, hasPrisonSentence, long-term imprisonment in South Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrisonSentence Context triple: [Radovan Krejcir, hasPrisonSentence, long-term imprisonment in South Africa]
-
A.
hasPrison
Indicates that one entity possesses, contains, or is the location of a prison associated with another entity.
-
B.
hasBeenImprisoned
Indicates that an entity has been confined or incarcerated in a prison or similar detention facility at some point in time.
-
C.
hasPrisonService
Indicates that an entity provides, manages, or is responsible for prison-related services or operations for another entity.
-
D.
hasBeenImprisonedBy
Indicates that one entity has been confined or incarcerated under the authority or control of another entity.
-
E.
sentencedTo
chosen
Indicates that an authority has officially assigned a specific punishment or penalty to an entity, typically as the outcome of a legal or disciplinary process.
- 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_69f349ccc290819089d8e82698e53cb6 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a03142a3a7081909bcfb683b44e2217 |
completed | May 12, 2026, 11:51 a.m. |
| PD | Predicate disambiguation | batch_6a031400af808190a72abf095e96c151 |
completed | May 12, 2026, 11:50 a.m. |
Created at: May 1, 2026, 2:01 a.m.