Triple
T11838132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Krugersdorp Prison |
E281574
|
entity |
| Predicate | hasRehabilitationPrograms |
P87761
|
FINISHED |
| Object | educational programs |
—
|
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: educational programs | Statement: [Krugersdorp Prison, hasRehabilitationPrograms, educational programs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRehabilitationPrograms Context triple: [Krugersdorp Prison, hasRehabilitationPrograms, educational programs]
-
A.
hasResidentialProgram
Indicates that an entity offers or is associated with a residential program where participants live on-site.
-
B.
hasInmatePrograms
chosen
Indicates that an entity provides, offers, or is associated with specific programs or services intended for inmates.
-
C.
hasHealthProgram
Indicates that an entity provides, administers, or is associated with a specific health-related program or initiative.
-
D.
hasImprovementProgram
Indicates that an entity is associated with, participates in, or is covered by a program specifically designed to improve its performance, condition, or quality.
-
E.
establishedProgram
Indicates that an entity has created and put into operation a formal program that is now in an active, ongoing state.
- 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_69d6ab276f8c8190b1966a0ef11349ac |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a63106b48190917817ec40d21a49 |
completed | April 10, 2026, 7:26 a.m. |
| PD | Predicate disambiguation | batch_69d8a254a57481908a1e6ad97919c416 |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:43 p.m.