Triple
T1370566
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yarra River |
E30103
|
entity |
| Predicate | passesThrough |
P225
|
FINISHED |
| Object | Hawthorn |
E135216
|
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: Hawthorn | Statement: [Yarra River, passesThrough, Hawthorn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hawthorn Context triple: [Yarra River, passesThrough, Hawthorn]
-
A.
Hawthorn
chosen
Hawthorn is an inner suburb of Melbourne, Australia, known for its historic architecture, leafy streets, and proximity to major educational institutions.
-
B.
Woodberry
Woodberry is a residential suburb located within the Maitland local government area in the Hunter Region of New South Wales, Australia.
-
C.
Mountain Ash
Mountain Ash is a former coal-mining town and community in the Cynon Valley of Rhondda Cynon Taf, South Wales.
-
D.
Aloysia
Aloysia is a feminine given name, historically used in European contexts and closely related to the name Louise.
-
E.
Frangula
Frangula is a genus of flowering shrubs and small trees, commonly known as buckthorns, found in temperate regions and valued for their ecological and medicinal properties.
- 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_69a498f912008190a376a98b207b2071 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c2d7b6008190bc0303b56959ba56 |
completed | March 1, 2026, 10:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acd47f25c48190a27f87909c15d7c3 |
completed | March 8, 2026, 1:44 a.m. |
Created at: March 1, 2026, 7:57 p.m.