Triple

T20242182
Position Surface form Disambiguated ID Type / Status
Subject Aschersleben station E498324 entity
Predicate servesSettlement P2741 FINISHED
Object Aschersleben 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: Aschersleben | Statement: [Aschersleben station, servesSettlement, Aschersleben]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aschersleben
Context triple: [Aschersleben station, servesSettlement, Aschersleben]
  • A. Aschersleben chosen
    Aschersleben is a historic town in the German state of Saxony-Anhalt, known as one of the oldest documented cities in central Germany.
  • B. Oschersleben
    Oschersleben is a town in the German state of Saxony-Anhalt, known for its motorsport race track Motorsport Arena Oschersleben.
  • C. Zerbst
    Zerbst is a historic town in Saxony-Anhalt, Germany, known as the birthplace of Catherine the Great and for its former role as a princely residence.
  • D. Zerbst
    Zerbst is a party in the landmark U.S. Supreme Court case Johnson v. Zerbst, which established the federal constitutional right to counsel for indigent defendants in criminal prosecutions.
  • E. Trakehnen
    Trakehnen was a renowned East Prussian stud farm and village, historically famous as the cradle of the Trakehner horse breed.
  • 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_69da6274c58c81909c646eabed6f4f30 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6716f9d248190a145f6883827ebbe completed April 20, 2026, 6:33 p.m.
Created at: April 11, 2026, 11:40 p.m.