Triple
T23363959
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Robberts Swart |
E593260
|
entity |
| Predicate | hasSurname |
P18
|
FINISHED |
| Object | Swart |
—
|
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: Swart | Statement: [Charles Robberts Swart, hasSurname, Swart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Swart Context triple: [Charles Robberts Swart, hasSurname, Swart]
-
A.
Swart
chosen
Swart is a surname of Afrikaans and Dutch origin, notably borne by Charles Robberts Swart, the first State President of South Africa.
-
B.
Schwaz
Schwaz is a historic silver-mining town in the Austrian state of Tyrol, known for its medieval center and alpine setting.
-
C.
Schwarza
Schwarza is a river in the Black Forest region of Baden-Württemberg, Germany, that serves as one of the headwaters of the Wutach.
-
D.
Blaak
Blaak is a central transport hub and urban square in Rotterdam, known for its metro and train station near landmarks like the Cube Houses and Markthal.
-
E.
Grauer
Grauer is a surname most prominently associated with Peter T. Grauer, the American businessman and longtime chairman of Bloomberg L.P.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e25d2593c88190bcdf4a716a94ccb2 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a0aac4248190a4663ed12aed6856 |
completed | April 29, 2026, 6:09 a.m. |
Created at: April 17, 2026, 5:31 p.m.