Triple

T17003343
Position Surface form Disambiguated ID Type / Status
Subject BVG Class H E412504 entity
Predicate operator P179 FINISHED
Object BVG 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 | Statement: [BVG Class H, operator, BVG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BVG
Context triple: [BVG Class H, operator, BVG]
  • A. BVG chosen
    BVG is Berlin’s main public transport company, operating the city’s U-Bahn, trams, buses, and ferries.
  • B. BVG Projekt GmbH
    BVG Projekt GmbH is a subsidiary company of Berlin’s public transport operator that specializes in planning and managing infrastructure and development projects for the city’s transit network.
  • C. BMVg
    BMVg is the commonly used abbreviation for Germany’s Federal Ministry of Defence, the government department responsible for the country’s military and defense policy.
  • D. VBG
    VBG is the abbreviated name of the German association of botanical gardens, Verband Botanischer Gärten e.V.
  • E. B-VG
    B-VG is the commonly used abbreviation for Austria’s Federal Constitutional Law, which forms the core of the country’s constitutional framework.
  • 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_69d886cb581c8190ab05f4b429c9cd85 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d37f8ba88190b8d32a1d09b6e6fd completed April 18, 2026, 6:54 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00dc2035848190bf299875d37c8ac7 completed May 10, 2026, 7:27 p.m.
Created at: April 10, 2026, 5:32 a.m.