Triple
T4149668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erongo Region |
E89872
|
entity |
| Predicate | containsSettlement |
P847
|
FINISHED |
| Object | Swakopmund |
E171457
|
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: Swakopmund | Statement: [Erongo Region, containsSettlement, Swakopmund]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Swakopmund Context triple: [Erongo Region, containsSettlement, Swakopmund]
-
A.
Swakopmund
chosen
Swakopmund is a coastal city in Namibia known for its German colonial architecture, cool Atlantic climate, and popularity as a tourist destination and adventure-sports hub.
-
B.
Lüderitz
Lüderitz is a coastal town in southwestern Namibia known for its Atlantic shoreline, nearby desert landscapes, and rich marine ecosystem influenced by the Benguela Current.
-
C.
Ondangwa
Ondangwa is a town in northern Namibia that serves as an important commercial and transport hub for the surrounding Oshana Region.
-
D.
Anseba
Anseba is a central region of Eritrea known for its diverse ethnic communities, agriculture, and the regional capital Keren.
-
E.
Lobamba
Lobamba is the traditional and legislative capital of Eswatini, serving as the seat of the Swazi monarchy and key national institutions.
- 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_69aed95a59a881909b26e70b42c6811a |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0273a038819087db092da234e767 |
completed | March 9, 2026, 5:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b589e457f48190b8ed8bd92e07b519 |
completed | March 14, 2026, 4:16 p.m. |
Created at: March 9, 2026, 3:43 p.m.