Triple
T22296423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kogelberg Mountains |
E551132
|
entity |
| Predicate | nearestTown |
P350
|
FINISHED |
| Object | Kleinmond |
—
|
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: Kleinmond | Statement: [Kogelberg Mountains, nearestTown, Kleinmond]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kleinmond Context triple: [Kogelberg Mountains, nearestTown, Kleinmond]
-
A.
Kleinmond
chosen
Kleinmond is a small coastal town in South Africa’s Western Cape, known for its scenic beaches, whale watching, and proximity to the biodiverse Kogelberg Biosphere Reserve.
-
B.
Lanseria
Lanseria is a town in the northwestern part of Johannesburg, South Africa, known primarily for hosting the privately owned Lanseria International Airport.
-
C.
Kommetjie
Kommetjie is a small coastal village on South Africa’s Cape Peninsula known for its surf breaks, long white beaches, and relaxed seaside atmosphere.
-
D.
Hartenbos
Hartenbos is a popular coastal holiday town and beach resort in South Africa’s Western Cape, near Mossel Bay, known for its family-friendly atmosphere and seaside tourism.
-
E.
Hlobyne
Hlobyne is a small town in central Ukraine located within Poltava Oblast, known for its agricultural and food-processing industries.
- 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_69e11e45fb848190a1b2ae21296e3a5f |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15720fba0819080f6c96f6df4f1e0 |
completed | April 29, 2026, 12:56 a.m. |
Created at: April 16, 2026, 8:41 p.m.