Triple

T20516392
Position Surface form Disambiguated ID Type / Status
Subject Marienplatz E503692 entity
Predicate connectsWith P37 FINISHED
Object Dienerstraße
Dienerstraße is a central street in Munich’s Old Town known for its shops, historic buildings, and proximity to Marienplatz.
 E1443542 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: Dienerstraße | Statement: [Marienplatz, connectsWith, Dienerstraße]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dienerstraße
Context triple: [Marienplatz, connectsWith, Dienerstraße]
  • A. Siesmayerstraße
    Siesmayerstraße is a street in Frankfurt am Main, Germany, known for bordering the historic Palmengarten botanical garden.
  • B. Niederkirchnerstraße
    Niederkirchnerstraße is a street in central Berlin, Germany, historically associated with Nazi-era government and security offices and now home to memorial sites such as the Topography of Terror.
  • C. Brehmstraße
    Brehmstraße is a street in Düsseldorf, Germany, best known for lending its name to the historic ice hockey arena Eisstadion an der Brehmstraße.
  • D. Karmarschstraße
    Karmarschstraße is a central shopping and traffic street in Hanover, Germany, running through the city center near Kröpcke square.
  • E. Benkertstraße
    Benkertstraße is a historic street located in Potsdam’s Dutch Quarter, known for its characteristic red-brick Dutch-style architecture.
  • 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: Dienerstraße
Triple: [Marienplatz, connectsWith, Dienerstraße]
Generated description
Dienerstraße is a central street in Munich’s Old Town known for its shops, historic buildings, and proximity to Marienplatz.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dienerstraße
Target entity description: Dienerstraße is a central street in Munich’s Old Town known for its shops, historic buildings, and proximity to Marienplatz.
  • A. Siesmayerstraße
    Siesmayerstraße is a street in Frankfurt am Main, Germany, known for bordering the historic Palmengarten botanical garden.
  • B. Niederkirchnerstraße
    Niederkirchnerstraße is a street in central Berlin, Germany, historically associated with Nazi-era government and security offices and now home to memorial sites such as the Topography of Terror.
  • C. Brehmstraße
    Brehmstraße is a street in Düsseldorf, Germany, best known for lending its name to the historic ice hockey arena Eisstadion an der Brehmstraße.
  • D. Karmarschstraße
    Karmarschstraße is a central shopping and traffic street in Hanover, Germany, running through the city center near Kröpcke square.
  • E. Benkertstraße
    Benkertstraße is a historic street located in Potsdam’s Dutch Quarter, known for its characteristic red-brick Dutch-style architecture.
  • 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_69e0b4b2aa788190ae9eb37c1d73b1f1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e69f41eee481908121e54c7bd691ca completed April 20, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08cd4978d88190a15cc708101c4750 completed May 16, 2026, 8:02 p.m.
NEDg Description generation batch_6a08d174278481909db394da2a7ff969 completed May 16, 2026, 8:20 p.m.
NED2 Entity disambiguation (via description) batch_6a08d28e02fc8190ab694673156ab0c0 completed May 16, 2026, 8:24 p.m.
Created at: April 16, 2026, 11:36 a.m.