Triple
T27103750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swan Hill line |
E686507
|
entity |
| Predicate | passengerServiceBrand |
P142506
|
FINISHED |
| Object |
V/Line Swan Hill service
V/Line Swan Hill service is a regional passenger train service in Victoria, Australia, operating under the V/Line brand between Melbourne and the town of Swan Hill.
|
E686507
|
NE FINISHED |
How this triple was built (3 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: V/Line Swan Hill service | Statement: [Swan Hill line, passengerServiceBrand, V/Line Swan Hill service]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: V/Line Swan Hill service Triple: [Swan Hill line, passengerServiceBrand, V/Line Swan Hill service]
Generated description
V/Line Swan Hill service is a regional passenger train service in Victoria, Australia, operating under the V/Line brand between Melbourne and the town of Swan Hill.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: passengerServiceBrand Context triple: [Swan Hill line, passengerServiceBrand, V/Line Swan Hill service]
-
A.
airlineBrand
Indicates that one entity functions as the commercial airline brand associated with, or operating under, another entity.
-
B.
airlineAssociatedBrand
Indicates that a brand is commercially or operationally associated with a particular airline, such as through co-branding, partnership, or subsidiary relationships.
-
C.
publicTransportBrand
chosen
Indicates that a public transport service, line, or vehicle operates under or is associated with a specific brand or branding entity.
-
D.
hasPassengerServicesTo
Indicates that a transportation provider operates passenger services connecting one location or entity to another.
-
E.
primaryPassengerOperatorOnRoute
Indicates that an operator is the main provider of passenger services on a specific route.
- F. None of above.
Provenance (6 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_69ef1489f8b481908e24a1985982bd26 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f6691f5e188190b12c7b2eb729a45e |
completed | May 2, 2026, 9:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a12480a91a881909410b5f6a4aa1708 |
completed | May 24, 2026, 12:36 a.m. |
| NEDg | Description generation | batch_6a124a032764819083399db3b9089018 |
completed | May 24, 2026, 12:44 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a124a8690ec8190853768e7cebe4b4e |
completed | May 24, 2026, 12:47 a.m. |
| PD | Predicate disambiguation | batch_69f66598d6008190a7ca8ff80399fd34 |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 27, 2026, 8:49 a.m.