Triple

T10128574
Position Surface form Disambiguated ID Type / Status
Subject Gniezno E226276 entity
Predicate hasTwinTown P919 FINISHED
Object Berdychiv E370669 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: Berdychiv | Statement: [Gniezno, hasTwinTown, Berdychiv]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berdychiv
Context triple: [Gniezno, hasTwinTown, Berdychiv]
  • A. Berdichev chosen
    Berdichev is a historic city in present-day Ukraine, long known as a major center of Jewish life and commerce in Eastern Europe.
  • B. Chortkiv
    Chortkiv is a historic town in western Ukraine known for its architectural landmarks and role as a local cultural and administrative center.
  • C. Zbarazh
    Zbarazh is a historic town in western Ukraine known for its medieval castle and role in regional political and military history.
  • D. Berezhany
    Berezhany is a historic town in western Ukraine’s Ternopil Oblast, known for its well-preserved Renaissance castle and multicultural heritage.
  • E. Drohobych
    Drohobych is a historic city in western Ukraine known for its medieval architecture, salt production heritage, and association with writer and artist Bruno Schulz.
  • 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_69ca843057b48190a86730167f5d6b98 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cdd2f0a0e881909267a83fbeb31f0c completed April 2, 2026, 2:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69e3c79bc53481908552af9ebd582edf completed April 18, 2026, 6:04 p.m.
Created at: March 30, 2026, 9:05 p.m.