Triple
T8151065
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Welkom |
E190332
|
entity |
| Predicate | isMiningTownIn |
P53613
|
FINISHED |
| Object | Free State goldfields |
—
|
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: Free State goldfields | Statement: [Welkom, isMiningTownIn, Free State goldfields]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isMiningTownIn Context triple: [Welkom, isMiningTownIn, Free State goldfields]
-
A.
foundedAsMiningTownIn
chosen
Indicates that a settlement or town was originally established as a mining town in the specified location or jurisdiction.
-
B.
wasRoyalMiningTownOf
Indicates that a town historically held official royal status and functioned as a designated center for mining activities under royal authority.
-
C.
hasMiningDistrict
Indicates that an entity possesses, contains, or is associated with a designated mining district within its domain or jurisdiction.
-
D.
hasMiningCommunities
Indicates that one entity possesses, contains, or is associated with communities whose primary activity is mining.
-
E.
isCompanyTownFor
Indicates that one location functions as a company town whose economy, services, or governance are predominantly controlled or dominated by a specific company.
- 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_69ca82be7ba8819087de0147e9292c83 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4481f19c8190aeec9bf029ad321b |
completed | March 31, 2026, 3:50 a.m. |
| PD | Predicate disambiguation | batch_69cb36a0847c8190af9038aef78319b3 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:37 p.m.