Triple

T16214694
Position Surface form Disambiguated ID Type / Status
Subject Mauerpark E393555 entity
Predicate operator P179 FINISHED
Object Grün Berlin GmbH E323226 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: Grün Berlin GmbH | Statement: [Mauerpark, operator, Grün Berlin GmbH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grün Berlin GmbH
Context triple: [Mauerpark, operator, Grün Berlin GmbH]
  • A. Grün Berlin GmbH chosen
    Grün Berlin GmbH is a state-owned company responsible for planning, developing, and managing major public parks and open spaces in Berlin.
  • B. Berliner Verkehrsbetriebe
    Berliner Verkehrsbetriebe is Berlin’s main public transport company, operating the city’s extensive network of U-Bahn trains, trams, and buses.
  • C. Berlin CSD e.V.
    Berlin CSD e.V. is the organizing association behind Berlin’s annual Christopher Street Day (CSD) parade and related events advocating for LGBTQ+ rights and visibility.
  • D. S-Bahn Berlin GmbH
    S-Bahn Berlin GmbH is the company responsible for operating Berlin’s urban rapid transit S-Bahn rail network.
  • E. Vereinigte Berlinische Bodenkredit-Aktiengesellschaft
    Vereinigte Berlinische Bodenkredit-Aktiengesellschaft was a German mortgage and land credit bank based in Berlin that played a role in financing real estate and related enterprises.
  • 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_69d87f1f5bd08190bd01cac0d5b9d2ef completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e227f393e08190be93400d754f0a2d completed April 17, 2026, 12:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a000794e6c881909c4521e4dd031971 completed May 10, 2026, 4:20 a.m.
Created at: April 10, 2026, 5:03 a.m.