Triple

T16271489
Position Surface form Disambiguated ID Type / Status
Subject Duke of Berg E395009 entity
Predicate hasEarlierSeat P91945 FINISHED
Object Windeck Castle E674350 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: Windeck Castle | Statement: [Duke of Berg, hasEarlierSeat, Windeck Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Windeck Castle
Context triple: [Duke of Berg, hasEarlierSeat, Windeck Castle]
  • A. Windeck Castle chosen
    Windeck Castle is a medieval hilltop castle ruin overlooking the town of Weinheim in southwestern Germany.
  • B. Waldeck Castle
    Waldeck Castle is a historic fortress in Hesse, Germany, long associated with the noble House of Waldeck and overlooking the Edersee reservoir.
  • C. Wulff Castle
    Wulff Castle is a historic, European-style mansion perched on the coastal rocks of Viña del Mar, Chile, now serving as a cultural and heritage landmark.
  • D. Engelbourg Castle
    Engelbourg Castle is a ruined medieval fortress overlooking the town of Thann in France’s Alsace region, known for its distinctive collapsed tower nicknamed the “Eye of the Witch.”
  • E. Allenstein Castle
    Allenstein Castle is a historic medieval fortress in Olsztyn, Poland, best known for its association with Nicolaus Copernicus, who lived and worked there.
  • 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_69d87f221d8081909b0b2063e7528ba2 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e246099dd081908e268a1a0cf8a373 completed April 17, 2026, 2:39 p.m.
NED1 Entity disambiguation (via context triple) batch_6a001f90d4088190915d701978f018a5 completed May 10, 2026, 6:02 a.m.
Created at: April 10, 2026, 5:05 a.m.