Triple
T23008010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Croajingolong National Park |
E572830
|
entity |
| Predicate | hasNearestTown |
P21721
|
FINISHED |
| Object | Mallacoota |
—
|
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: Mallacoota | Statement: [Croajingolong National Park, hasNearestTown, Mallacoota]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mallacoota Context triple: [Croajingolong National Park, hasNearestTown, Mallacoota]
-
A.
Mallacoota
chosen
Mallacoota is a small coastal town in eastern Victoria, Australia, known for its remote beaches, fishing, and proximity to Croajingolong National Park.
-
B.
Widgiemooltha
Widgiemooltha is a small rural locality in Western Australia known historically for gold and nickel mining.
-
C.
Manjimup
Manjimup is a rural town in Western Australia known for its timber industry, agriculture, and truffle production.
-
D.
Amaroo
Amaroo is a residential suburb in the Gungahlin district of Canberra, Australian Capital Territory.
-
E.
Tooronga
Tooronga is a suburb in Melbourne, Victoria, Australia, known for its residential character and proximity to major shopping and transport hubs.
- 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1835802a881908fe817c3fa728a82 |
completed | April 29, 2026, 4:04 a.m. |
Created at: April 17, 2026, 3:51 p.m.