Triple
T20707983
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vygruppen |
E508953
|
entity |
| Predicate | ticketingSystem |
P3383
|
FINISHED |
| Object | Vy app |
—
|
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: Vy app | Statement: [Vygruppen, ticketingSystem, Vy app]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vy app Context triple: [Vygruppen, ticketingSystem, Vy app]
-
A.
Vy mobile app
chosen
Vy mobile app is a mobile application that allows users to plan journeys and purchase tickets for Vy’s regional train services in Norway.
-
B.
Mich App
Mich App is the standard legal citation abbreviation for the Michigan Appellate Reports, which publish decisions of the Michigan Court of Appeals.
-
C.
Appin
Appin is a coastal district in the Scottish Highlands known for its scenic landscapes, historic sites, and views over Loch Linnhe.
-
D.
Appin
Appin is a small town in New South Wales, Australia, known for its rural character and historical significance in the Macarthur region.
-
E.
ABC app
ABC app is a streaming platform from the ABC television network that lets viewers watch live and on-demand ABC programming, including college football broadcasts.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4c40ad88190b81f77695366d328 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1952e888190877b79933970f7b0 |
completed | April 21, 2026, 12:15 a.m. |
Created at: April 16, 2026, 12:14 p.m.