Triple

T7712591
Position Surface form Disambiguated ID Type / Status
Subject Marburg E174796 entity
Predicate hasLandmark P105 FINISHED
Object Marburg Castle E239055 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: Marburg Castle | Statement: [Marburg, hasLandmark, Marburg Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marburg Castle
Context triple: [Marburg, hasLandmark, Marburg Castle]
  • A. Marburg Castle chosen
    Marburg Castle is a historic hilltop fortress and former residence of the Landgraves of Hesse, overlooking the town of Marburg and serving today as a museum and cultural venue.
  • B. Dillenburg Castle
    Dillenburg Castle was a significant Renaissance-era stronghold in Dillenburg, Germany, historically associated with the House of Nassau and the early life of William the Silent.
  • C. Marksburg Castle
    Marksburg Castle is a well-preserved medieval hilltop fortress overlooking the Rhine River in Germany, renowned as one of the few castles in the region never destroyed.
  • D. Homburg Castle
    Homburg Castle is a historic German castle in Bad Homburg vor der Höhe, Hesse, known for its role as a royal residence and its well-preserved architecture and gardens.
  • E. Wartburg Castle
    Wartburg Castle is a medieval fortress in Eisenach, Germany, famed as the place where Martin Luther translated the New Testament into German while in hiding.
  • 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_69c6995c463c8190a14458036249d419 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c702c96e388190898165f84d646c0e completed March 27, 2026, 10:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8acd3e9f88190adf42ab42c21b722 completed March 29, 2026, 4:38 a.m.
Created at: March 27, 2026, 4:04 p.m.