Triple
T26363185
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarbert ferry terminal |
E660261
|
entity |
| Predicate | primaryFerryOperator |
P5933
|
FINISHED |
| Object | Caledonian MacBrayne |
—
|
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: Caledonian MacBrayne | Statement: [Tarbert ferry terminal, primaryFerryOperator, Caledonian MacBrayne]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryFerryOperator Context triple: [Tarbert ferry terminal, primaryFerryOperator, Caledonian MacBrayne]
-
A.
ferryOperator
chosen
Indicates that one entity operates, manages, or runs a ferry service for another entity or in a particular context.
-
B.
ferryOperatorType
Indicates the type or category of operator responsible for running a ferry service.
-
C.
shipOperator
Indicates the entity that is responsible for operating, managing, or running a ship.
-
D.
ferryNetworkBrand
Indicates the brand or commercial identity under which a ferry network operates or is marketed.
-
E.
ferryFlightCarrier
Indicates that one carrier operates a ferry (non-revenue repositioning) flight on behalf of another carrier.
- 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_69ee8126d52c8190bc0b34337c2c9aa8 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69fddf721c1481909301a0f379368f10 |
completed | May 8, 2026, 1:04 p.m. |
| PD | Predicate disambiguation | batch_69fddda1ae7c8190b5848ff9a9e39826 |
completed | May 8, 2026, 12:57 p.m. |
Created at: April 26, 2026, 10:53 p.m.