Triple
T22332646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Simon's Town |
E552059
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Fish Hoek |
—
|
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: Fish Hoek | Statement: [Simon's Town, nearbySettlement, Fish Hoek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fish Hoek Context triple: [Simon's Town, nearbySettlement, Fish Hoek]
-
A.
Fish Hoek
chosen
Fish Hoek is a coastal suburb and popular beach town on the False Bay shoreline of Cape Town, South Africa, known for its family-friendly swimming beach and relaxed residential character.
-
B.
Kalk Bay harbour
Kalk Bay harbour is a historic working fishing harbour and popular tourist spot on the False Bay coast of Cape Town, known for its colourful boats, fresh seafood, and scenic views.
-
C.
Whale Bay
Whale Bay is a renowned surf beach near Raglan, New Zealand, famous for its long, world-class left-hand point break and scenic coastal setting.
-
D.
Whale Bay
Whale Bay is a picturesque, secluded beach cove in Northland, New Zealand, known for its clear waters, white sand, and coastal walking tracks.
-
E.
De Hoek
De Hoek is a railway station in the Brussels area that forms part of the region’s suburban and commuter rail network.
- 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_69e11e482f788190b78d1588fc26d606 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1577c1a5c819092ac468a7d5ce499 |
completed | April 29, 2026, 12:57 a.m. |
Created at: April 16, 2026, 8:43 p.m.