Triple
T15542661
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laing's Nek |
E370519
|
entity |
| Predicate | nearbyTown |
P3883
|
FINISHED |
| Object | Volksrust |
E779580
|
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: Volksrust | Statement: [Laing's Nek, nearbyTown, Volksrust]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Volksrust Context triple: [Laing's Nek, nearbyTown, Volksrust]
-
A.
Volksrust
chosen
Volksrust is a small South African town in Mpumalanga province, historically known as a strategic railway and agricultural center near the KwaZulu-Natal border.
-
B.
Geseke
Geseke is a small town in western Germany located in the historical region of Westphalia.
-
C.
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.
-
D.
Witpoortjie
Witpoortjie is a residential suburb in Roodepoort, South Africa, known for its proximity to the Witpoortjie Falls and the Walter Sisulu National Botanical Garden.
-
E.
Lutzenberg
Lutzenberg is a small municipality in the canton of Appenzell Ausserrhoden in northeastern Switzerland.
- 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_69d85cc521a08190921fb50319dddc34 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04432c3808190bb5b653bf8de30c6 |
completed | April 16, 2026, 2:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff4558677881908704ac86c12e1fc4 |
completed | May 9, 2026, 2:31 p.m. |
Created at: April 10, 2026, 4:07 a.m.