Triple
T38021825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mandla Dlamini |
E948655
|
entity |
| Predicate | hasSurnameOriginRegion |
P179683
|
FINISHED |
| Object | Southern Africa |
—
|
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: Southern Africa | Statement: [Mandla Dlamini, hasSurnameOriginRegion, Southern Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSurnameOriginRegion Context triple: [Mandla Dlamini, hasSurnameOriginRegion, Southern Africa]
-
A.
hasSurnameRegionAssociation
Indicates that there is a relationship between a surname and a geographic region, such as origin, prevalence, or cultural association.
-
B.
surnameLikelyOriginRegion
chosen
Indicates the geographic region from which a person’s surname is most likely to have originated.
-
C.
hasNameOrigin
Indicates that the origin or source of an entity’s name is specified by the related entity.
-
D.
hasSurnameEthymology
Indicates that an entity’s surname originates from, or is derived based on, a specified source, language, or etymological root.
-
E.
familyNameOriginType
Indicates the type or source of origin associated with a person's family name.
- 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_69f76efc10448190aff5fb566b98f952 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a0076c0a5c4819088b17b95511b93ed |
completed | May 10, 2026, 12:14 p.m. |
| PD | Predicate disambiguation | batch_6a007638a67c81909c091335142260ab |
completed | May 10, 2026, 12:12 p.m. |
Created at: May 3, 2026, 4:20 p.m.