Triple

T1088575
Position Surface form Disambiguated ID Type / Status
Subject Saaremaa E24108 entity
Predicate knownFor P22 FINISHED
Object medieval Kuressaare Castle E123540 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: medieval Kuressaare Castle | Statement: [Saaremaa, knownFor, medieval Kuressaare Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: medieval Kuressaare Castle
Context triple: [Saaremaa, knownFor, medieval Kuressaare Castle]
  • A. Kuressaare Castle chosen
    Kuressaare Castle is a well-preserved medieval stone fortress and former bishop’s residence located in the town of Kuressaare on Saaremaa Island in Estonia.
  • B. 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.
  • C. Kaunas Castle
    Kaunas Castle is a historic Gothic defensive fortress in Kaunas, Lithuania, notable as one of the country’s oldest stone castles and a key medieval stronghold.
  • D. Rosenborg Castle
    Rosenborg Castle is a 17th-century Renaissance castle in Copenhagen, Denmark, renowned for housing the Danish crown jewels and royal regalia.
  • 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_69a49404428c819092dcc9632f5f7b8b completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4b97d85708190a1630256648aa4a2 completed March 1, 2026, 10:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac4c243cbc81908d6101faad628fc8 completed March 7, 2026, 4:02 p.m.
Created at: March 1, 2026, 7:42 p.m.