Triple

T4314916
Position Surface form Disambiguated ID Type / Status
Subject Left-bank Ukraine E94163 entity
Predicate containsHistoricalCity P43430 FINISHED
Object Sumy E315609 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: Sumy | Statement: [Left-bank Ukraine, containsHistoricalCity, Sumy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sumy
Context triple: [Left-bank Ukraine, containsHistoricalCity, Sumy]
  • A. Sumy chosen
    Sumy is a regional city in northeastern Ukraine known as the administrative center of Sumy Oblast and an important cultural, educational, and industrial hub.
  • B. Rivne
    Rivne is a city in western Ukraine that serves as an important regional administrative, economic, and cultural center.
  • C. Ternopil
    Ternopil is a city in western Ukraine known as a regional cultural and economic center with a historic old town and a picturesque lakeside setting.
  • D. Uzhhorod
    Uzhhorod is a historic city in western Ukraine near the Slovak and Hungarian borders, known for its multicultural heritage and as the administrative center of Zakarpattia Oblast.
  • E. Khmelnytskyi
    Khmelnytskyi is a regional city in western Ukraine known as an important administrative, economic, and cultural center.
  • 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_69b3451886588190a3dd1305ea7c58dc completed March 12, 2026, 10:58 p.m.
NER Named-entity recognition batch_69b3563eab24819088add9180af2ce3c completed March 13, 2026, 12:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69be921df91881909c257fbd3c46073c completed March 21, 2026, 12:42 p.m.
Created at: March 12, 2026, 11:12 p.m.