Triple
T19000879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geelong railway line |
E464945
|
entity |
| Predicate | currentMainRoute |
P6298
|
FINISHED |
| Object | via Regional Rail Link corridor |
—
|
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: via Regional Rail Link corridor | Statement: [Geelong railway line, currentMainRoute, via Regional Rail Link corridor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: currentMainRoute Context triple: [Geelong railway line, currentMainRoute, via Regional Rail Link corridor]
-
A.
currentUseOfRoute
Indicates that a particular route is presently being used for a specific purpose, activity, or traffic flow.
-
B.
previousRoute
Indicates that one route directly precedes another in an ordered sequence of routes.
-
C.
primaryRoute
chosen
Indicates that one route is designated as the main or preferred path among possible alternatives between locations.
-
D.
originalRoute
Indicates that one route is the initial or primary path from which another route is derived, modified, or compared.
-
E.
parentRoute
Indicates that one route serves as the direct hierarchical ancestor or container of another route within a routing structure.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6863cf4819096e471d19f9a714c |
completed | April 20, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f88e0c81908cb20f08bf24cd32 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 12:01 p.m.