Triple

T6366129
Position Surface form Disambiguated ID Type / Status
Subject Bezirk Halle E143233 entity
Predicate hadRuralDistrict P56414 FINISHED
Object Kreis Zerbst E626160 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: Kreis Zerbst | Statement: [Bezirk Halle, hadRuralDistrict, Kreis Zerbst]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kreis Zerbst
Context triple: [Bezirk Halle, hadRuralDistrict, Kreis Zerbst]
  • A. Kreis Belzig
    Kreis Belzig was a former rural district in the German Democratic Republic, located in the Potsdam region of the state of Brandenburg.
  • B. Kreis Köthen chosen
    Kreis Köthen was a former rural district in the German Democratic Republic, located within the administrative region of Bezirk Halle.
  • C. Kreis Sebnitz
    Kreis Sebnitz was a former rural district in the German Democratic Republic, located in the Bezirk Dresden region of Saxony and centered around the town of Sebnitz.
  • D. Kreis Querfurt
    Kreis Querfurt was a former rural district in the German Democratic Republic, located in the southern part of what is now the state of Saxony-Anhalt.
  • E. Kreis Apolda
    Kreis Apolda was a former rural district in the German Democratic Republic, located within the administrative region of Bezirk Erfurt.
  • 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_69c008d8c61081908bcaf61510d881ed completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c068106e18819087ed2e9841d2b365 completed March 22, 2026, 10:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69c79c6ec470819088f16fd762d3c7d7 completed March 28, 2026, 9:16 a.m.
Created at: March 22, 2026, 4:32 p.m.