Triple
T9618519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Surry Hills |
E232280
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Redfern |
E344903
|
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: Redfern | Statement: [Surry Hills, adjacentTo, Redfern]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Redfern Context triple: [Surry Hills, adjacentTo, Redfern]
-
A.
Redfern
chosen
Redfern is an inner-city suburb of Sydney, Australia, known for its major railway station and rich Aboriginal and working-class history.
-
B.
Greendykes
Greendykes is a residential area in the southeast of Edinburgh, Scotland, known for its post-war housing and ongoing urban regeneration.
-
C.
Crows Nest
Crows Nest is a vibrant lower North Shore suburb of Sydney, Australia, known for its bustling dining and nightlife scene.
-
D.
Minto
Minto is a small rural town and municipality in southwestern Ontario, Canada, known for its agricultural community and small-town character.
-
E.
Lane Cove
Lane Cove is a leafy, affluent residential suburb on Sydney’s Lower North Shore known for its village-style shopping precinct and proximity to extensive bushland and waterways.
- 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_69ca84867bb88190b4b57dd5a56d5691 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9ab0a15481908945b50c622b71b9 |
completed | April 1, 2026, 10:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d17965cce08190862ea8a48addf0a2 |
completed | April 4, 2026, 8:49 p.m. |
Created at: March 30, 2026, 8:09 p.m.