Triple
T2698022
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yancowinna County, New South Wales |
E58558
|
entity |
| Predicate | isRemoteFrom |
P37959
|
FINISHED |
| Object | eastern population centres of New South Wales |
—
|
LITERAL 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: eastern population centres of New South Wales | Statement: [Yancowinna County, New South Wales, isRemoteFrom, eastern population centres of New South Wales]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isRemoteFrom Context triple: [Yancowinna County, New South Wales, isRemoteFrom, eastern population centres of New South Wales]
-
A.
isMoreRemoteThan
chosen
Indicates that one entity is located at a greater distance or in a more out-of-the-way location compared to another entity.
-
B.
isFrom
Indicates that one entity originates, comes, or has been sent from another entity or source.
-
C.
isFromRegion
Indicates that one entity originates from, is associated with, or belongs to a specified geographic region.
-
D.
hasOriginIn
Indicates that something begins, arises, or is derived from a specified source, place, or cause.
-
E.
isOffsetFrom
Indicates that one entity’s position, value, or occurrence is displaced by a specified amount or direction relative to 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_69ab4ac269e481909cb317d79e68b75b |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abda322af48190833b8a3c006db236 |
completed | March 7, 2026, 7:56 a.m. |
| PD | Predicate disambiguation | batch_69abd81ea5d88190ab5c8f8b8064b931 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:55 p.m.