Triple

T20667820
Position Surface form Disambiguated ID Type / Status
Subject Freising district E507938 entity
Predicate contains P35 FINISHED
Object Hallbergmoos 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: Hallbergmoos | Statement: [Freising district, contains, Hallbergmoos]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hallbergmoos
Context triple: [Freising district, contains, Hallbergmoos]
  • A. Hallbergmoos chosen
    Hallbergmoos is a municipality in Bavaria, Germany, known for hosting major aerospace and technology companies near Munich.
  • B. Haigerloch
    Haigerloch is a small historic town in the Zollernalb district of Baden-Württemberg, Germany, known for its picturesque old town and former role in Germany’s World War II nuclear research.
  • C. Sulzemoos
    Sulzemoos is a small municipality in Bavaria, Germany, located northwest of Munich in the district of Dachau.
  • D. Röhrmoos
    Röhrmoos is a municipality in Upper Bavaria, Germany, situated within the district of Dachau.
  • E. Hasliberg
    Hasliberg is a Swiss alpine village and municipality in the canton of Bern, known for its mountain scenery and ski and hiking resort facilities.
  • 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_69e0b4c059bc81908ea762cd73ea4424 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b5c4c4608190ae17da4a59e5ae80 completed April 20, 2026, 11:24 p.m.
Created at: April 16, 2026, 11:44 a.m.