Triple
T24287277
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Williamstown line |
E605703
|
entity |
| Predicate | baysideAccess |
P138699
|
FINISHED |
| Object | Hobsons Bay foreshore at Williamstown |
—
|
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: Hobsons Bay foreshore at Williamstown | Statement: [Williamstown line, baysideAccess, Hobsons Bay foreshore at Williamstown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: baysideAccess Context triple: [Williamstown line, baysideAccess, Hobsons Bay foreshore at Williamstown]
-
A.
bayAccess
chosen
Indicates that an entity has the ability, right, or means to reach, use, or interact with a specific bay or bay area.
-
B.
accessPointOnStatenIslandSide
Indicates that the access point is located on the Staten Island side of a relevant boundary, structure, or route.
-
C.
cityAccess
Indicates that an entity has permission or the ability to enter, use, or reach a particular city.
-
D.
accessPointOnBrooklynSide
Indicates that the access point is located on the Brooklyn side of a relevant boundary or structure.
-
E.
accessTown
Indicates that an entity has the ability or permission to enter or make use of a particular town.
- 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_69e295480d0c8190846fc3c2e2da1d4c |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f28f56cdc08190a1e06f67dffd4769 |
completed | April 29, 2026, 11:08 p.m. |
| PD | Predicate disambiguation | batch_69f1c457a2908190993824395b3c365d |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 18, 2026, 12:08 a.m.