Triple

T6051379
Position Surface form Disambiguated ID Type / Status
Subject Bezirk Dresden E134800 entity
Predicate borderedBy P224 FINISHED
Object Bezirk Cottbus E543213 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: Bezirk Cottbus | Statement: [Bezirk Dresden, borderedBy, Bezirk Cottbus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bezirk Cottbus
Context triple: [Bezirk Dresden, borderedBy, Bezirk Cottbus]
  • A. Bezirk Cottbus chosen
    Bezirk Cottbus was an administrative district in the former East Germany, located in the southeast of the country and centered around the city of Cottbus.
  • B. Bezirk Dresden
    Bezirk Dresden was an administrative district centered on the city of Dresden that functioned as one of the key regional divisions of the former East Germany.
  • C. Bezirk Gera
    Bezirk Gera was an administrative district of the former East Germany, centered around the city of Gera in the state of Thuringia.
  • D. Bezirk Leipzig
    Bezirk Leipzig was an administrative district in the former East Germany centered around the city of Leipzig.
  • E. Bezirk Schwerin
    Bezirk Schwerin was an administrative district in the former East Germany, centered around the city of Schwerin and existing from the 1952 territorial reform until German reunification in 1990.
  • 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_69c00877b6d4819096b0e163728b73a3 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c056f66cb08190a782cdd038f26b93 completed March 22, 2026, 8:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69c5e3b108c48190a11ad1a9440fcb12 completed March 27, 2026, 1:56 a.m.
Created at: March 22, 2026, 4:09 p.m.