Triple

T17703392
Position Surface form Disambiguated ID Type / Status
Subject Prince Felix of Bourbon-Parma E441365 entity
Predicate residence P75 FINISHED
Object Fischbach Castle E444241 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: Fischbach Castle | Statement: [Prince Felix of Bourbon-Parma, residence, Fischbach Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fischbach Castle
Context triple: [Prince Felix of Bourbon-Parma, residence, Fischbach Castle]
  • A. Fischbach Castle chosen
    Fischbach Castle is a historic royal residence in Luxembourg closely associated with the Grand Ducal family.
  • B. Friedberg Castle
    Friedberg Castle is a historic fortress in the former Imperial City of Friedberg in Hesse, Germany, notable for its large medieval complex and well-preserved defensive structures.
  • C. Forchtenstein Castle
    Forchtenstein Castle is a massive medieval fortress in Burgenland, Austria, best known as a stronghold and treasury of the aristocratic Esterházy family.
  • D. Betzdorf Castle
    Betzdorf Castle is a historic Luxembourgish castle notable as the birthplace of Henri, Grand Duke of Luxembourg.
  • E. Runkel Castle
    Runkel Castle is a medieval hill castle in Runkel, Hesse, Germany, notable for its well-preserved fortifications and long association with regional nobility.
  • 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_69d8b9ea20b48190ace88bb46b01e6a9 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4729528b88190bd8a104f6f6d4e69 completed April 19, 2026, 6:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0242ec0b708190add75f3bd08fc446 completed May 11, 2026, 8:58 p.m.
Created at: April 10, 2026, 10:05 a.m.