Triple

T12838703
Position Surface form Disambiguated ID Type / Status
Subject Sumy Oblast E306986 entity
Predicate hasMajorCity P316 FINISHED
Object Lebedyn
Lebedyn is a city in northeastern Ukraine known for its historical architecture and role as a local cultural and administrative center.
E1004144 NE FINISHED

How this triple was built (4 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: Lebedyn | Statement: [Sumy Oblast, hasMajorCity, Lebedyn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lebedyn
Context triple: [Sumy Oblast, hasMajorCity, Lebedyn]
  • A. Lebedus
    Lebedus was an ancient Greek city of Ionia on the western coast of Asia Minor, known as a minor but strategically located coastal settlement involved in regional trade and politics.
  • B. Barysaw
    Barysaw is a city in Belarus known as an important industrial and transportation center northeast of Minsk.
  • C. Zvenyhorodka
    Zvenyhorodka is a town in central Ukraine that serves as a local administrative and cultural center within Cherkasy Oblast.
  • D. Bogrod
    Bogrod is a goblin banker who works at Gringotts Wizarding Bank in the Harry Potter series.
  • E. Bronnitsy
    Bronnitsy is a historic town in Russia known for its jewelry-making traditions and its location southeast of Moscow along the Moskva River.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lebedyn
Triple: [Sumy Oblast, hasMajorCity, Lebedyn]
Generated description
Lebedyn is a city in northeastern Ukraine known for its historical architecture and role as a local cultural and administrative center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lebedyn
Target entity description: Lebedyn is a city in northeastern Ukraine known for its historical architecture and role as a local cultural and administrative center.
  • A. Lebedus
    Lebedus was an ancient Greek city of Ionia on the western coast of Asia Minor, known as a minor but strategically located coastal settlement involved in regional trade and politics.
  • B. Barysaw
    Barysaw is a city in Belarus known as an important industrial and transportation center northeast of Minsk.
  • C. Zvenyhorodka
    Zvenyhorodka is a town in central Ukraine that serves as a local administrative and cultural center within Cherkasy Oblast.
  • D. Bogrod
    Bogrod is a goblin banker who works at Gringotts Wizarding Bank in the Harry Potter series.
  • E. Bronnitsy
    Bronnitsy is a historic town in Russia known for its jewelry-making traditions and its location southeast of Moscow along the Moskva River.
  • F. None of above. chosen

Provenance (5 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_69d7bdf52b94819096d6f0ba4ab50a98 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96ff11b4481909fb2f92c46186853 completed April 10, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f68edd30e881909062e8f91f614990 completed May 2, 2026, 11:55 p.m.
NEDg Description generation batch_69f68f8d2ca08190a385635fb6130a9f completed May 2, 2026, 11:58 p.m.
NED2 Entity disambiguation (via description) batch_69f69033a66481908bf4ae23fced5983 completed May 3, 2026, midnight
Created at: April 9, 2026, 5:35 p.m.