Triple
T5794563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bloem |
E128475
|
entity |
| Predicate | governmentBranchHosted |
P479
|
FINISHED |
| Object | judicial branch of 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: judicial branch of South Africa | Statement: [Bloem, governmentBranchHosted, judicial branch of South Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: governmentBranchHosted Context triple: [Bloem, governmentBranchHosted, judicial branch of South Africa]
-
A.
federalGovernmentBranchHosted
Indicates that a particular branch of the federal government served as the host or organizing body for an event, activity, or entity.
-
B.
governmentBranch
chosen
Indicates that one entity functions as an official division or branch within the structure of a government.
-
C.
governmentBranchServed
Indicates that an entity has served in or been a member of a particular branch of government.
-
D.
governmentCategory
Indicates the type or classification of a government associated with an entity.
-
E.
governmentCenter
Indicates that a location serves as the primary administrative or political hub for a government or governing body.
- 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_69c00845ca68819081a2ce3ecca577f7 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c02b1304588190b59a18fb7b70a60f |
completed | March 22, 2026, 5:46 p.m. |
| PD | Predicate disambiguation | batch_69c021d477008190946113f9859eeb90 |
completed | March 22, 2026, 5:07 p.m. |
Created at: March 22, 2026, 3:51 p.m.