Triple
T14134967
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gariep River |
E350266
|
entity |
| Predicate | passesNear |
P416
|
FINISHED |
| Object | Upington |
E329324
|
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: Upington | Statement: [Gariep River, passesNear, Upington]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Upington Context triple: [Gariep River, passesNear, Upington]
-
A.
Upington
chosen
Upington is a town in South Africa’s Northern Cape province, serving as a key regional center on the Orange River and a gateway to nearby desert and wildlife attractions.
-
B.
Williton
Williton is a large village and civil parish in Somerset, England, serving as an important local hub near the coast and the Quantock Hills.
-
C.
Trowbridge
Trowbridge is a small unincorporated community located in Sutter County, California.
-
D.
Trowbridge
Trowbridge is a market town in Wiltshire, England, known as the administrative centre of the county.
-
E.
Hawkesbury Upton
Hawkesbury Upton is a small rural village in South Gloucestershire, England, known for its traditional Cotswold stone buildings and annual literature festival.
- 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_69d827865f608190b311820428ae027b |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de610e949c8190852d336c9d12bfd0 |
completed | April 14, 2026, 3:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcdf14439c81908b2a9999a35cc346 |
completed | May 7, 2026, 6:51 p.m. |
Created at: April 9, 2026, 11:57 p.m.