Triple
T25328692
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NSW TrainLink XPT Sydney–Albury service |
E635088
|
entity |
| Predicate | borderServed |
P12818
|
FINISHED |
| Object | New South Wales–Victoria border |
—
|
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: New South Wales–Victoria border | Statement: [NSW TrainLink XPT Sydney–Albury service, borderServed, New South Wales–Victoria border]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderServed Context triple: [NSW TrainLink XPT Sydney–Albury service, borderServed, New South Wales–Victoria border]
-
A.
servesBorder
Indicates that one entity functions as a boundary or border for another entity.
-
B.
borderWithin
Indicates that one region’s border lies entirely inside the boundary of another region.
-
C.
borderRegion
chosen
Indicates a region that lies along or near the boundary separating two distinct geographic or political areas.
-
D.
borderArea
Indicates that an area lies along or near the boundary between two regions, countries, or territories.
-
E.
borderDefinedBy
Indicates that the boundary or limit of one entity is determined, shaped, or delineated by another 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_69e75a9908108190a95427a97020632a |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f638d11c988190af7fd4572b08e038 |
completed | May 2, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69f63706b6008190993577193c85ff50 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 21, 2026, 1:30 p.m.