Triple

T20443692
Position Surface form Disambiguated ID Type / Status
Subject Burghausen old town E501459 entity
Predicate hasLandmark P105 FINISHED
Object Burghausen Castle 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: Burghausen Castle | Statement: [Burghausen old town, hasLandmark, Burghausen Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Burghausen Castle
Context triple: [Burghausen old town, hasLandmark, Burghausen Castle]
  • A. Burghausen Castle chosen
    Burghausen Castle is a medieval hilltop fortress in Bavaria, Germany, renowned for being one of the longest castle complexes in the world.
  • B. Wittelsbach Castle
    Wittelsbach Castle was the ancestral stronghold of the Bavarian noble dynasty that later became known as the House of Wittelsbach.
  • C. Plassenburg Castle
    Plassenburg Castle is a historic hilltop fortress in Kulmbach, Germany, renowned for its Renaissance architecture and housing one of the world’s largest collections of tin figures.
  • D. Ortenburg Castle
    Ortenburg Castle is a historic fortress complex in Bautzen, Germany, notable for its medieval origins and its role as a former seat of regional power in Upper Lusatia.
  • E. Forchtenstein Castle
    Forchtenstein Castle is a massive medieval fortress in Burgenland, Austria, best known as a stronghold and treasury of the aristocratic Esterházy family.
  • 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_69e0b4ac0a1c81908845d0f8a56abce8 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e68cfa7dd08190883a37e3480b152c completed April 20, 2026, 8:30 p.m.
Created at: April 16, 2026, 11:32 a.m.