Triple
T35239367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ferry to Stony Point |
E1017468
|
entity |
| Predicate | hasEndpointIsland |
P170747
|
FINISHED |
| Object | Phillip Island |
—
|
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: Phillip Island | Statement: [ferry to Stony Point, hasEndpointIsland, Phillip Island]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEndpointIsland Context triple: [ferry to Stony Point, hasEndpointIsland, Phillip Island]
-
A.
hasIslandTerminus
chosen
Indicates that something (such as a route, line, or connection) ends or terminates on an island.
-
B.
hasIslandConnection
Indicates that there exists a connection or link between entities that specifically involves or passes through an island.
-
C.
hasIsland
Indicates that one entity possesses, contains, or includes an island as part of its domain, territory, or structure.
-
D.
hasEndpointStation
Indicates that something (such as a route, line, or service) has a specific station as one of its terminal endpoints.
-
E.
hasPrimaryEndpoint
Indicates that an entity designates another entity as its main or most important endpoint or target location.
- 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_69f76de235048190b990070c23c51b6b |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd64bc86848190a49f451a8fc5cf1e |
completed | May 8, 2026, 4:21 a.m. |
| PD | Predicate disambiguation | batch_69fd5ff4a648819090756d90fd195d9a |
completed | May 8, 2026, 4 a.m. |
Created at: May 3, 2026, 4:02 p.m.