Triple
T27327038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Birchip |
E689679
|
entity |
| Predicate | siloArtTrail |
P142999
|
FINISHED |
| Object | Silo Art Trail in 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: Silo Art Trail in Victoria | Statement: [Birchip, siloArtTrail, Silo Art Trail in Victoria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: siloArtTrail Context triple: [Birchip, siloArtTrail, Silo Art Trail in Victoria]
-
A.
artSite
chosen
Indicates a relationship where a location or site is used for, associated with, or designated as a place for art creation, display, or related artistic activities.
-
B.
hasArtScene
Indicates that a place or community possesses an active or notable community of artistic activity, events, and institutions.
-
C.
exhibitionGalleries
Indicates that an exhibition is displayed or hosted in one or more specific galleries.
-
D.
streetArt
Indicates that an entity creates, displays, or is associated with artistic works placed in public urban spaces, typically on streets or buildings.
-
E.
exhibitsBeyond
Indicates that one entity displays or demonstrates something to a degree that surpasses or goes further than another reference point or standard.
- 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_69ef355d4cb08190ab032c0a2e7d3753 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f627eea1d08190aa3733b460c43b6e |
completed | May 2, 2026, 4:35 p.m. |
| PD | Predicate disambiguation | batch_69f620e4b1c88190a17940251abc68fd |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 11:36 a.m.