Triple
T27103899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New South Wales border |
E686511
|
entity |
| Predicate | hasSouthernBoundaryWith |
P117551
|
FINISHED |
| Object | Victoria |
—
|
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: Victoria | Statement: [New South Wales border, hasSouthernBoundaryWith, Victoria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSouthernBoundaryWith Context triple: [New South Wales border, hasSouthernBoundaryWith, Victoria]
-
A.
hasSouthBorder
chosen
Indicates that one entity shares its southern boundary or border with another entity.
-
B.
southeasternBoundaryFollows
Indicates that the southeastern boundary of one entity follows, aligns with, or is defined by the boundary or feature of another entity.
-
C.
southernBoundaryReference
Indicates that one entity is used as the reference or defining limit for the southern boundary of another entity.
-
D.
northernBorderLiesAcross
Indicates that the northern border of one region extends across or passes through the area of another region.
-
E.
boundaryTypeSouth
Indicates the type or nature of the boundary that lies to the south of a given 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_69f68805b4848190b75da14996d52a38 |
completed | May 2, 2026, 11:25 p.m. |
| PD | Predicate disambiguation | batch_69f68609c0b08190a8e1238a4d97c270 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 27, 2026, 8:49 a.m.