Triple

T3452796
Position Surface form Disambiguated ID Type / Status
Subject Teutonic Order E72830 entity
Predicate capital P234 FINISHED
Object Marienburg Castle E362890 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: Marienburg Castle | Statement: [Teutonic Order, capital, Marienburg Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marienburg Castle
Context triple: [Teutonic Order, capital, Marienburg Castle]
  • A. Marienburg Castle chosen
    Marienburg Castle is a massive medieval fortress in Malbork, Poland, renowned as one of the largest brick castles in the world and a former stronghold of the Teutonic Knights.
  • B. 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.
  • C. Świdwin Castle
    Świdwin Castle is a historic medieval fortress in the town of Świdwin in northwestern Poland, notable for its Gothic architecture and role in regional history.
  • D. Marienberg Fortress
    Marienberg Fortress is a historic hilltop castle complex overlooking Würzburg, Germany, known for its medieval fortifications and panoramic views of the Main River valley.
  • E. Dresden Castle
    Dresden Castle is a historic royal residence in Dresden, Germany, renowned for its Renaissance and Baroque architecture and its museums housing the famed Green Vault treasure collection.
  • 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_69ad85b12a908190a1d10a6b03b4f8ae completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adbaa2f5ec81909ced93c01e8fe38b completed March 8, 2026, 6:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69b37e59178881909facfe90004c9d99 completed March 13, 2026, 3:02 a.m.
Created at: March 8, 2026, 3:16 p.m.