Triple
T27103900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New South Wales border |
E686511
|
entity |
| Predicate | hasWesternBoundaryWith |
P224
|
FINISHED |
| Object | South Australia |
—
|
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: South Australia | Statement: [New South Wales border, hasWesternBoundaryWith, South Australia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWesternBoundaryWith Context triple: [New South Wales border, hasWesternBoundaryWith, South Australia]
-
A.
boundaryTypeWest
Indicates the type or nature of the boundary that exists on the western side of an entity or area.
-
B.
borderedBy
chosen
Indicates that one entity shares a common boundary or edge with another entity.
-
C.
westernBoundaryReference
Indicates the reference feature or limit that defines the western boundary of an entity or area.
-
D.
isWesternmostPartOf
Indicates that one entity is the furthest to the west within the geographic extent or boundary of another entity.
-
E.
easternBoundaryFormedBy
Indicates that the eastern boundary of an area, region, or object is defined or formed by a specified feature or entity.
- F. None of above.
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_69ef1489f8b481908e24a1985982bd26 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f64dbbaefc8190952b8320bf4397d8 |
completed | May 2, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69f64cacd2c08190aed8a1761d0da679 |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 27, 2026, 8:49 a.m.