Triple

T8741195
Position Surface form Disambiguated ID Type / Status
Subject Terespol E207503 entity
Predicate hasNearbyCity P350 FINISHED
Object Biała Podlaska E364564 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: Biała Podlaska | Statement: [Terespol, hasNearbyCity, Biała Podlaska]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Biała Podlaska
Context triple: [Terespol, hasNearbyCity, Biała Podlaska]
  • A. Biała Podlaska chosen
    Biała Podlaska is a city in eastern Poland near the Belarusian border, known as a local economic and cultural center of the Lublin Voivodeship.
  • B. Radzyń Podlaski
    Radzyń Podlaski is a historic town in eastern Poland known for its Baroque Potocki Palace and role as a local cultural and administrative center.
  • C. Biłgoraj
    Biłgoraj is a town in eastern Poland known for its traditional wooden architecture and location near the Roztocze region.
  • D. Białogard
    Białogard is a historic town in northwestern Poland, located in the West Pomeranian Voivodeship on the Parsęta River.
  • E. Włodawa
    Włodawa is a town in eastern Poland near the borders with Belarus and Ukraine, known for its multicultural heritage and proximity to the former Sobibor extermination camp.
  • 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_69ca835a03a081909d4d4cd01a18c9fb completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5d4a0cf481909c770cb39fd00fcd completed March 31, 2026, 11:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f08ec96fe88190b791e6f50f39173f completed April 28, 2026, 10:41 a.m.
Created at: March 30, 2026, 6:38 p.m.