Triple

T19786140
Position Surface form Disambiguated ID Type / Status
Subject Frankenberg, Hesse E475272 entity
Predicate hasLandmark P105 FINISHED
Object Frankenberg town hall NE NERFINISHED

How this triple was built (3 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: Frankenberg town hall | Statement: [Frankenberg, Hesse, hasLandmark, Frankenberg town hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frankenberg town hall
Context triple: [Frankenberg, Hesse, hasLandmark, Frankenberg town hall]
  • A. Brackenheim town hall
    Brackenheim town hall is the main municipal building and administrative center of the town of Brackenheim in Baden-Württemberg, Germany.
  • B. Bramsche town hall
    Bramsche town hall is the central municipal building that houses the local government and administrative offices of the town of Bramsche in Lower Saxony, Germany.
  • C. Kitzingen town hall
    Kitzingen town hall is a historic municipal building in the Bavarian town of Kitzingen, Germany, known for its distinctive architecture and role as the seat of local government.
  • D. Forchheim town hall
    Forchheim town hall is a historic municipal building in the Bavarian town of Forchheim, noted for its traditional architecture and role as the seat of local government.
  • E. Erzhausen town hall
    Erzhausen town hall is the main administrative and civic building of the municipality of Erzhausen, serving as the center for local government functions and public services.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Frankenberg town hall
Target entity description: Frankenberg town hall is a historic municipal building in Frankenberg, Hesse, Germany, noted for its traditional architecture and role as the center of local government.
  • A. Brackenheim town hall
    Brackenheim town hall is the main municipal building and administrative center of the town of Brackenheim in Baden-Württemberg, Germany.
  • B. Bramsche town hall
    Bramsche town hall is the central municipal building that houses the local government and administrative offices of the town of Bramsche in Lower Saxony, Germany.
  • C. Kitzingen town hall
    Kitzingen town hall is a historic municipal building in the Bavarian town of Kitzingen, Germany, known for its distinctive architecture and role as the seat of local government.
  • D. Forchheim town hall
    Forchheim town hall is a historic municipal building in the Bavarian town of Forchheim, noted for its traditional architecture and role as the seat of local government.
  • E. Erzhausen town hall
    Erzhausen town hall is the main administrative and civic building of the municipality of Erzhausen, serving as the center for local government functions and public services.
  • F. None of above. chosen

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_69d8e51b014081908b263e167370529a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65387d3348190a31f9c2f9bc1c6d9 completed April 20, 2026, 4:25 p.m.
Created at: April 10, 2026, 1:49 p.m.