Triple
T22303746
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wonthaggi |
E551321
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Inverloch |
—
|
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: Inverloch | Statement: [Wonthaggi, near, Inverloch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Inverloch Context triple: [Wonthaggi, near, Inverloch]
-
A.
Wooroonah
Wooroonah is a rural locality situated within the Banana Shire region of Queensland, Australia.
-
B.
Beenleigh
Beenleigh is a suburban town in Queensland, Australia, known historically for its sugarcane industry and rum distillery, and now forming part of the Brisbane–Gold Coast urban corridor.
-
C.
Lakes Entrance
chosen
Lakes Entrance is a popular coastal town in eastern Victoria, Australia, known for its extensive network of inland waterways, fishing, and tourism.
-
D.
Wendouree
Wendouree is a residential and commercial suburb located in the city of Ballarat in Victoria, Australia.
-
E.
Waroona
Waroona is a small rural town in Western Australia known for its agricultural activities, nearby forests and lakes, and role as a service centre within the Peel region.
- 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_69e11e46c0188190800181a4233f28fe |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15725de488190a32006cd99dd4a67 |
completed | April 29, 2026, 12:56 a.m. |
Created at: April 16, 2026, 8:41 p.m.