Triple
T11605576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Henri van Breda |
E275248
|
entity |
| Predicate | caseDescribedAs |
P37427
|
FINISHED |
| Object | high-profile criminal case 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: high-profile criminal case in South Africa | Statement: [Henri van Breda, caseDescribedAs, high-profile criminal case in South Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: caseDescribedAs Context triple: [Henri van Breda, caseDescribedAs, high-profile criminal case in South Africa]
-
A.
indexCaseDescription
Indicates a textual description that explains the circumstances, characteristics, or details of the initial or primary case in a set of related cases.
-
B.
conditionsDescribedAs
Indicates that one entity is described or characterized in terms of certain conditions specified by another entity.
-
C.
caseTypes
Indicates the types or categories of cases associated with or applicable to an entity or situation.
-
D.
describedIn
Indicates that information about an entity is contained or documented within a specified source, such as a text, document, or media.
-
E.
laterDescribedAs
chosen
Indicates that an entity is referred to or characterized by a particular description or label at a later time.
- 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_69d6aaf84b548190ac072e4fb89ae18f |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d895502e0081909ee9c3d45d26cd91 |
completed | April 10, 2026, 6:14 a.m. |
| PD | Predicate disambiguation | batch_69d85dd20d188190863d1190d4c16048 |
completed | April 10, 2026, 2:17 a.m. |
Created at: April 8, 2026, 9:38 p.m.