Triple

T20765466
Position Surface form Disambiguated ID Type / Status
Subject Verbotene Stadt E511083 entity
Predicate locatedIn P40 FINISHED
Object Zossen NE NERFINISHED

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: Zossen | Statement: [Verbotene Stadt, locatedIn, Zossen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zossen
Context triple: [Verbotene Stadt, locatedIn, Zossen]
  • A. Zossen chosen
    Zossen is a town in Brandenburg, Germany, historically notable as a major military command center, including serving as a key headquarters area during the Soviet occupation after World War II.
  • B. Schönwalde
    Schönwalde is a locality within the municipality of Wandlitz in the state of Brandenburg, Germany.
  • C. Schorfheide
    Schorfheide is a large forested and lake-rich area in Brandenburg, Germany, known for its protected natural landscapes and historical use as a royal and political hunting ground.
  • D. Hellersdorf
    Hellersdorf is a locality in eastern Berlin, Germany, known for its large prefabricated housing estates built during the GDR era.
  • E. Stolzenhagen
    Stolzenhagen is a village and locality within the municipality of Wandlitz in the state of Brandenburg, Germany.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4ca01148190ac018e57e0cab46f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c24bde0c8190b46986b89bf2e037 completed April 21, 2026, 12:18 a.m.
Created at: April 16, 2026, 12:36 p.m.