Triple

T4060870
Position Surface form Disambiguated ID Type / Status
Subject Berlin U-Bahn line U7 E86206 entity
Predicate depot P14646 FINISHED
Object Britz-Süd depot
Britz-Süd depot is a maintenance and storage facility for trains of Berlin’s U7 underground line, located near the Britz-Süd station in the Neukölln district.
E410416 NE FINISHED

How this triple was built (4 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: Britz-Süd depot | Statement: [Berlin U-Bahn line U7, depot, Britz-Süd depot]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Britz-Süd depot
Context triple: [Berlin U-Bahn line U7, depot, Britz-Süd depot]
  • A. Fürth depot
    Fürth depot is a maintenance and storage facility serving the Nuremberg U-Bahn rapid transit system in the Fürth area of Germany.
  • B. Elsau depot
    Elsau depot is a tram maintenance and storage facility serving the Strasbourg tramway network in Strasbourg, France.
  • C. Südkreuz station
    Südkreuz station is a major Berlin transport hub serving regional, long-distance, and S-Bahn trains in the southern part of the city.
  • D. Grefsen depot
    Grefsen depot is a major tram depot in Oslo, Norway, serving as a key maintenance and storage facility for the city’s tram network.
  • E. Butovo depot
    Butovo depot is the maintenance and storage facility serving the Butovskaya Line of the Moscow Metro in Moscow, Russia.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Britz-Süd depot
Triple: [Berlin U-Bahn line U7, depot, Britz-Süd depot]
Generated description
Britz-Süd depot is a maintenance and storage facility for trains of Berlin’s U7 underground line, located near the Britz-Süd station in the Neukölln district.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Britz-Süd depot
Target entity description: Britz-Süd depot is a maintenance and storage facility for trains of Berlin’s U7 underground line, located near the Britz-Süd station in the Neukölln district.
  • A. Fürth depot
    Fürth depot is a maintenance and storage facility serving the Nuremberg U-Bahn rapid transit system in the Fürth area of Germany.
  • B. Elsau depot
    Elsau depot is a tram maintenance and storage facility serving the Strasbourg tramway network in Strasbourg, France.
  • C. Südkreuz station
    Südkreuz station is a major Berlin transport hub serving regional, long-distance, and S-Bahn trains in the southern part of the city.
  • D. Grefsen depot
    Grefsen depot is a major tram depot in Oslo, Norway, serving as a key maintenance and storage facility for the city’s tram network.
  • E. Butovo depot
    Butovo depot is the maintenance and storage facility serving the Butovskaya Line of the Moscow Metro in Moscow, Russia.
  • F. None of above. chosen

Provenance (5 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_69aed93c69208190a4efac0efe3cd69b completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefbd4acb0819093bcffcd05ed8e6f completed March 9, 2026, 4:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b562a98c488190a7e77cd46ff998bc completed March 14, 2026, 1:29 p.m.
NEDg Description generation batch_69b5637e72948190989169b0a46916a8 completed March 14, 2026, 1:32 p.m.
NED2 Entity disambiguation (via description) batch_69b563fc4cb081908ba0f1a799338a8c completed March 14, 2026, 1:34 p.m.
Created at: March 9, 2026, 3:38 p.m.