Triple

T21324951
Position Surface form Disambiguated ID Type / Status
Subject Bryansk E525726 entity
Predicate sisterCity P1072 FINISHED
Object Plock NE NERFINISHED

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: Plock | Statement: [Bryansk, sisterCity, Plock]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Plock
Context triple: [Bryansk, sisterCity, Plock]
  • A. Piła
    Piła is a city in northwestern Poland known as a regional economic and transport center in the Greater Poland Voivodeship.
  • B. Płock chosen
    Płock is a historic city in central Poland known for its medieval architecture and scenic location on the banks of the Vistula River.
  • C. Szczecinek
    Szczecinek is a town in northwestern Poland known for its lakeside setting, historic architecture, and role as a local economic and cultural center in the West Pomeranian Voivodeship.
  • D. Pałuki
    Pałuki is a historical and ethnographic region in north-central Poland, known for its distinctive folk culture, wooden architecture, and numerous lakes.
  • E. Łeba
    Łeba is a river in northern Poland that flows through the Pomeranian region to the Baltic Sea.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b51b90788190a4dd823d962626da completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e77ed7732c8190a0e7aec6e7cbcef2 completed April 21, 2026, 1:42 p.m.
Created at: April 16, 2026, 4:41 p.m.