Triple

T15596708
Position Surface form Disambiguated ID Type / Status
Subject Bramsche E374909 entity
Predicate hasTwinTown P919 FINISHED
Object Haldensleben E594406 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: Haldensleben | Statement: [Bramsche, hasTwinTown, Haldensleben]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haldensleben
Context triple: [Bramsche, hasTwinTown, Haldensleben]
  • A. Haldensleben chosen
    Haldensleben is a town in the German state of Saxony-Anhalt, known as an administrative and economic center with historical roots dating back to the Middle Ages.
  • B. Harzgerode
    Harzgerode is a small historic town in the eastern Harz Mountains of central Germany, known for its mining heritage and surrounding forested landscapes.
  • C. Sangerhausen
    Sangerhausen is a town in the German state of Saxony-Anhalt, known for its historic mining heritage and its renowned Europa-Rosarium rose garden.
  • D. Anhalt-Plötzkau
    Anhalt-Plötzkau was a small principality within the Holy Roman Empire that formed part of the fragmented territorial landscape of the larger Anhalt region in central Germany.
  • E. Sondershausen
    Sondershausen is a small town in the German state of Thuringia, known for its historic castle, former role as a princely residence, and long tradition of mining and music.
  • 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_69d85cce25008190b13b52745fbd719b completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e5f9db8819083abf80f01f32b3d completed April 16, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00580789c08190994c5c71525aadc6 completed May 10, 2026, 10:03 a.m.
Created at: April 10, 2026, 4:12 a.m.