Triple
T17989957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chief of the South African National Defence Force |
E430340
|
entity |
| Predicate | isTopLevelCommand |
P84727
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Chief of the South African National Defence Force, isTopLevelCommand, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isTopLevelCommand Context triple: [Chief of the South African National Defence Force, isTopLevelCommand, true]
-
A.
hasTopLevel
Indicates that one entity is the highest or primary element within a hierarchy or structure relative to another entity.
-
B.
hasHigherCommand
chosen
Indicates that one entity holds a superior or higher-level command authority over another entity.
-
C.
containsCommand
Indicates that one entity includes or embeds a command directed at or executable by another entity.
-
D.
isUnifiedCommand
Indicates that multiple entities operate under a single, integrated command structure or authority.
-
E.
hasTopLevelCategory
Indicates that an entity is assigned to a primary or highest-level category within a classification or taxonomy.
- 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_69d8b90364248190a37381adea932f42 |
completed | April 10, 2026, 8:46 a.m. |
| NER | Named-entity recognition | batch_69e4b29e47a88190be58b79c73d3e652 |
completed | April 19, 2026, 10:46 a.m. |
| PD | Predicate disambiguation | batch_69e3f90039e4819080527f860dca042e |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:23 a.m.