Triple

T21896091
Position Surface form Disambiguated ID Type / Status
Subject Celle E540682 entity
Predicate hasOldTown P295 FINISHED
Object Altstadt Celle 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: Altstadt Celle | Statement: [Celle, hasOldTown, Altstadt Celle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Altstadt Celle
Context triple: [Celle, hasOldTown, Altstadt Celle]
  • A. city of Celle chosen
    The city of Celle is a historic town in Lower Saxony, Germany, known for its well-preserved medieval old town and numerous timber-framed houses.
  • B. Altstadt Warburg
    Altstadt Warburg is the historic old town district of Warburg, Germany, characterized by its medieval street layout, half-timbered houses, and preserved fortifications.
  • C. Tecklenburg
    Tecklenburg is a historic small town in North Rhine-Westphalia, Germany, known for its medieval architecture and open-air theater.
  • D. Mainburg
    Mainburg is a Bavarian town in southern Germany known for its hop-growing industry and role in the Hallertau beer region.
  • E. Lemgo
    Lemgo is a historic town in the Lippe district of North Rhine-Westphalia, Germany, known for its well-preserved medieval architecture and Hanseatic heritage.
  • 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_69e0c47a95908190ae3e19b716accb3d completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f11fc700c08190a470fe1ad76c8509 completed April 28, 2026, 8:59 p.m.
Created at: April 16, 2026, 7:07 p.m.