Triple

T963420
Position Surface form Disambiguated ID Type / Status
Subject Henri, Grand Duke of Luxembourg E20783 entity
Predicate residence P75 FINISHED
Object Berg Castle E92750 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: Berg Castle | Statement: [Henri, Grand Duke of Luxembourg, residence, Berg Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berg Castle
Context triple: [Henri, Grand Duke of Luxembourg, residence, Berg Castle]
  • A. Berg Castle chosen
    Berg Castle is the principal royal residence of the Grand Ducal family of Luxembourg, located near the town of Colmar-Berg.
  • B. Hellenstein Castle
    Hellenstein Castle is a historic hilltop fortress overlooking Heidenheim an der Brenz in southern Germany, known for its medieval architecture and panoramic views.
  • C. Celle Castle
    Celle Castle is a historic ducal palace in Celle, Germany, notable as a former residence of the House of Brunswick-Lüneburg and an important example of Renaissance and Baroque architecture.
  • D. Betzdorf Castle
    Betzdorf Castle is a historic Luxembourgish castle notable as the birthplace of Henri, Grand Duke of Luxembourg.
  • E. Tre Kronor Castle
    Tre Kronor Castle was the medieval royal castle and principal residence of Swedish monarchs in Stockholm until it was largely destroyed by fire in 1697.
  • 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_69a493b21f2881908132dcf45dcd2f36 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b416cf4c8190bd685227db25fb53 completed March 1, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac1cd72fe88190a7cdfe1afc123edd completed March 7, 2026, 12:40 p.m.
Created at: March 1, 2026, 7:40 p.m.