Triple
T9121968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | N11 |
E218874
|
entity |
| Predicate | connectsCity |
P4245
|
FINISHED |
| Object | Ermelo |
E176019
|
NE 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: Ermelo | Statement: [N11, connectsCity, Ermelo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ermelo Context triple: [N11, connectsCity, Ermelo]
-
A.
Ermelo
chosen
Ermelo is a key agricultural and transport hub town located in South Africa’s Mpumalanga province.
-
B.
Klerksdorp
Klerksdorp is a historic mining and agricultural city in South Africa’s North West Province, known as one of the country’s oldest European settlements and a regional economic hub.
-
C.
Harrismith
Harrismith is a town in the Free State province of South Africa, situated near the Drakensberg mountains and serving as an important transport and agricultural hub.
-
D.
Winburg
Winburg is a small historic town in South Africa’s Free State province, known as one of the country’s oldest Voortrekker settlements.
-
E.
Uitenhage
Uitenhage is a South African town in the Eastern Cape known historically for its automotive industry and as part of the greater Port Elizabeth (Gqeberha) urban area.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca83dddd548190983b96c664f7f367 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8b46dac8190bde88205c85f596a |
completed | April 1, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d047c55a988190bf2dd63a0d0a2743 |
completed | April 3, 2026, 11:05 p.m. |
Created at: March 30, 2026, 7:17 p.m.