Triple

T17940887
Position Surface form Disambiguated ID Type / Status
Subject István Dobó de Ruszka E448582 entity
Predicate residence P75 FINISHED
Object Eger 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: Eger Castle | Statement: [István Dobó de Ruszka, residence, Eger Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eger Castle
Context triple: [István Dobó de Ruszka, residence, Eger Castle]
  • A. Castle of Eger chosen
    The Castle of Eger is a historic Hungarian stronghold famed for its pivotal role in defending against Ottoman invasions during the 16th century.
  • B. Horthy Castle
    Horthy Castle is a historic manor house in Kenderes, Hungary, best known as the family residence of Regent Miklós Horthy.
  • C. Diósgyőr Castle
    Diósgyőr Castle is a medieval Hungarian fortress in the city of Miskolc, renowned for its well-preserved ruins and role as a former royal residence.
  • D. Łańcut Castle
    Łańcut Castle is a renowned aristocratic residence in southeastern Poland, famous for its well-preserved Baroque architecture, opulent interiors, and extensive park complex.
  • E. Salgó Castle
    Salgó Castle is a medieval hilltop fortress in northern Hungary, known for its panoramic views and historical ruins overlooking the surrounding landscape.
  • 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_69d8b9f79d14819095540856928f0e25 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4ad95f4608190b1ebb45944218f07 completed April 19, 2026, 10:25 a.m.
Created at: April 10, 2026, 10:21 a.m.