Triple
T24158935
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bredasdorp |
E598775
|
entity |
| Predicate | localMunicipality |
P74637
|
FINISHED |
| Object | Cape Agulhas Local Municipality |
—
|
NE NERFINISHED |
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: Cape Agulhas Local Municipality | Statement: [Bredasdorp, localMunicipality, Cape Agulhas Local Municipality]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: localMunicipality Context triple: [Bredasdorp, localMunicipality, Cape Agulhas Local Municipality]
-
A.
municipality
Indicates that one entity is a municipality (a local administrative unit) in which the other entity is located or which it governs.
-
B.
localGovernmentAreaOf
chosen
Indicates that one entity is the local government area within whose jurisdiction or administrative boundaries the other entity is located.
-
C.
mainMunicipality
Indicates that one municipality serves as the primary or central administrative municipality associated with another entity or area.
-
D.
isMunicipalHomeOf
Indicates that a municipality serves as the official home base or hosting location for a particular entity or organization.
-
E.
municipalityName
Indicates the official name assigned to a municipality.
- 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_69e288cb0a3081909ef221744f274384 |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1e0e7f8e481909c55ae66bf7b16e9 |
completed | April 29, 2026, 10:43 a.m. |
| PD | Predicate disambiguation | batch_69f176585f3481909beb907de252cd98 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:31 p.m.