Triple

T12640662
Position Surface form Disambiguated ID Type / Status
Subject Grodno Region E301887 entity
Predicate hasHistoricSite P1098 FINISHED
Object Old Grodno Castle E286644 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: Old Grodno Castle | Statement: [Grodno Region, hasHistoricSite, Old Grodno Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Old Grodno Castle
Context triple: [Grodno Region, hasHistoricSite, Old Grodno Castle]
  • A. Old Grodno Castle chosen
    Old Grodno Castle is a historic medieval fortress and former royal residence in Hrodna, Belarus, overlooking the Neman River.
  • B. New Grodno Castle
    New Grodno Castle is a historic royal residence and architectural landmark in the city of Hrodna, Belarus.
  • C. Nesvizh Castle
    Nesvizh Castle is a historic residential castle complex in Belarus renowned as a former Radziwiłł family seat and a UNESCO World Heritage Site noted for its architectural and cultural significance.
  • D. Ostroh Castle
    Ostroh Castle is a historic medieval fortress in the city of Ostroh in western Ukraine, long associated with the influential Ostrogski noble family and the cultural life of the region.
  • E. Königsberg Castle
    Königsberg Castle was a historic Prussian fortress and royal residence in Königsberg, notable as a political and cultural center of the Kingdom of Prussia.
  • 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_69d7bdec9f9c8190b4bac675b7588211 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9614ae6ac8190b42acbf2b0331fda completed April 10, 2026, 8:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f668754acc8190b5585dbd35387867 completed May 2, 2026, 9:11 p.m.
Created at: April 9, 2026, 5:17 p.m.