Triple

T2958983
Position Surface form Disambiguated ID Type / Status
Subject Imperial Castle in Poznań E79999 entity
Predicate ownedBy P347 FINISHED
Object City of Poznań E14540 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: City of Poznań | Statement: [Imperial Castle in Poznań, ownedBy, City of Poznań]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: City of Poznań
Context triple: [Imperial Castle in Poznań, ownedBy, City of Poznań]
  • A. Poznań chosen
    Poznań is a historic and economically significant city in western Poland, known for its medieval Old Town, role as an early center of Polish statehood, and status as a major academic and industrial hub.
  • B. Gniezno
    Gniezno is a historic city in west-central Poland, renowned as the country’s first capital and an early center of Polish statehood and Christianity.
  • C. Toruń
    Toruń is a historic city in northern Poland, renowned for its well-preserved medieval Old Town and as the birthplace of astronomer Nicolaus Copernicus.
  • D. Zamość
    Zamość is a Renaissance-planned city in southeastern Poland, renowned for its well-preserved Old Town and UNESCO World Heritage status.
  • E. Tarnów
    Tarnów is a historic city in southern Poland known for its well-preserved Old Town, Renaissance architecture, and cultural heritage.
  • 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_69ad8b1341848190bd19dbf46892887d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad992c4c7c819084b5bef299255181 completed March 8, 2026, 3:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1de92f04c8190967ec290cba891a6 completed March 11, 2026, 9:28 p.m.
Created at: March 8, 2026, 2:57 p.m.