Triple

T1087844
Position Surface form Disambiguated ID Type / Status
Subject Vistula River E24092 entity
Predicate flowsThrough P225 FINISHED
Object Sandomierz E198380 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: Sandomierz | Statement: [Vistula River, flowsThrough, Sandomierz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sandomierz
Context triple: [Vistula River, flowsThrough, Sandomierz]
  • A. Sandomierz chosen
    Sandomierz is a historic town in southeastern Poland, known for its well-preserved Old Town, medieval architecture, and picturesque location on the Vistula River.
  • B. Wadowice
    Wadowice is a historic town in southern Poland best known as the birthplace of Pope John Paul II.
  • C. Nowy Sącz
    Nowy Sącz is a historic city in southern Poland known for its well-preserved Old Town, cultural heritage, and role as a local economic and administrative center.
  • D. Tarnobrzeg
    Tarnobrzeg is a city in southeastern Poland known historically for its sulfur mining industry and location along the Vistula River.
  • 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_69a49404428c819092dcc9632f5f7b8b completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4b97c64a88190bf1119fdd4940bf3 completed March 1, 2026, 10:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69ae0a966a6c81909d1d21c489340134 completed March 8, 2026, 11:47 p.m.
Created at: March 1, 2026, 7:42 p.m.