Triple

T14265805
Position Surface form Disambiguated ID Type / Status
Subject BVG E353639 entity
Predicate mobileApp P14571 FINISHED
Object BVG Fahrinfo E353639 NE FINISHED

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: BVG Fahrinfo | Statement: [BVG, mobileApp, BVG Fahrinfo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BVG Fahrinfo
Context triple: [BVG, mobileApp, BVG Fahrinfo]
  • A. RegionalBahn
    RegionalBahn is a category of regional passenger trains in Germany that provide relatively frequent, short- to medium-distance services connecting cities and smaller towns.
  • B. Bonn public transport network
    The Bonn public transport network is an integrated system of buses, trams, and regional trains serving the city of Bonn and its surrounding districts in Germany.
  • C. Frankfurt public transport network
    The Frankfurt public transport network is an integrated system of trams, buses, S-Bahn, and U-Bahn services that provides comprehensive urban and regional mobility across Frankfurt and its surrounding areas.
  • D. BVG chosen
    BVG is Berlin’s main public transport company, operating the city’s U-Bahn, trams, buses, and ferries.
  • E. HAFAS: GOS
    HAFAS: GOS is the public transport timetable system code used to identify Goslar railway station in Germany.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d8278c43e08190824146f4632b89a5 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6357a8188190ba518a486521052b completed April 14, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd326551b08190ae8fe220a6422339 completed May 8, 2026, 12:46 a.m.
Created at: April 10, 2026, 1:09 a.m.