Triple
T35586470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spirit of Tasmania |
E1028371
|
entity |
| Predicate | previousRouteTerminus |
P200108
|
FINISHED |
| Object | Melbourne |
—
|
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: Melbourne | Statement: [Spirit of Tasmania, previousRouteTerminus, Melbourne]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousRouteTerminus Context triple: [Spirit of Tasmania, previousRouteTerminus, Melbourne]
-
A.
previousRoute
Indicates that one route directly precedes another in an ordered sequence of routes.
-
B.
mainRouteTerminus
Indicates that a location serves as a primary endpoint or terminus for a given route.
-
C.
usesFormerRouteOf
Indicates that one route, service, or pathway currently follows all or part of the alignment or path that was previously used by another route.
-
D.
nextRoute
Indicates that one route directly follows another in a defined sequence or ordering of routes.
-
E.
originalRoute
Indicates that one route is the initial or primary path from which another route is derived, modified, or compared.
- F. None of above. chosen
Provenance (4 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_69f76e0495a081909beced418558c0b4 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff7595c9bc8190982c6e6e07a0c78f |
completed | May 9, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69ff715432a88190a25670d26614bde2 |
completed | May 9, 2026, 5:39 p.m. |
| PDg | Predicate description generation | batch_69ff7594c6c081909e812e4e04e63530 |
completed | May 9, 2026, 5:57 p.m. |
Created at: May 3, 2026, 4:04 p.m.