Triple
T13953122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kwinana Freeway |
E335583
|
entity |
| Predicate | crosses |
P416
|
FINISHED |
| Object | Swan River |
—
|
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: Swan River | Statement: [Kwinana Freeway, crosses, Swan River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Swan River Context triple: [Kwinana Freeway, crosses, Swan River]
-
A.
Swan River
chosen
The Swan River is a major waterway in Western Australia that flows through the city of Perth and is central to its landscape, recreation, and history.
-
B.
Swan River
Swan River is a river flowing through the Una district, known for supporting local ecosystems and communities in that region.
-
C.
William River
William River is a river in northern Saskatchewan, Canada, that drains remote boreal and shield landscapes before emptying into Lake Athabasca.
-
D.
Arthur River
Arthur River is a river in New Zealand’s Fiordland region that drains alpine landscapes and carries the waters of notable features such as Sutherland Falls toward the sea.
-
E.
Williams River
The Williams River is a river in New South Wales, Australia, that flows through the Hunter Region and contributes to its agricultural and ecological landscape.
- 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_69d81c6081b88190b53e317c3370c8fe |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e146720819085d0f5eae558b7a4 |
completed | April 14, 2026, 12:07 p.m. |
Created at: April 9, 2026, 10:17 p.m.