Triple

T15092756
Position Surface form Disambiguated ID Type / Status
Subject Świdwin Castle E360461 entity
Predicate locatedIn P40 FINISHED
Object Świdwin E526225 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: Świdwin | Statement: [Świdwin Castle, locatedIn, Świdwin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Świdwin
Context triple: [Świdwin Castle, locatedIn, Świdwin]
  • A. Świdwin chosen
    Świdwin is a historic town in northwestern Poland, known for its medieval castle and location in the West Pomeranian Voivodeship.
  • B. Koszalin
    Koszalin is a city in northwestern Poland near the Baltic Sea, known as a regional cultural and economic center.
  • C. Bydgoszcz
    Bydgoszcz is a major city in northern Poland known as an important economic, cultural, and academic center on the Brda and Vistula rivers.
  • D. Ostróda
    Ostróda is a town in northern Poland known for its lakeside setting, tourism, and role as a local economic and cultural center.
  • E. Świnoujście
    Świnoujście is a Polish port city and seaside resort on the Baltic Sea, known for its wide beaches, spa facilities, and strategic location at the mouth of the Świna River.
  • 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_69d85a035aa88190b52a139d3a1b7b6d completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0027925788190b955fdc6626adf7d completed April 15, 2026, 9:26 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00dbf2567c81909ab6054ade27afac completed May 10, 2026, 7:26 p.m.
Created at: April 10, 2026, 3:04 a.m.