Triple

T2753906
Position Surface form Disambiguated ID Type / Status
Subject Zamość E61054 entity
Predicate twinTown P1072 FINISHED
Object Zhovkva
Zhovkva is a historic town in western Ukraine known for its well-preserved Renaissance architecture and multicultural heritage.
E367729 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: Zhovkva | Statement: [Zamość, twinTown, Zhovkva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zhovkva
Context triple: [Zamość, twinTown, Zhovkva]
  • A. Ivano-Frankivsk
    Ivano-Frankivsk is a historic city in western Ukraine known as a cultural, economic, and administrative center of the Carpathian region.
  • B. Vinnytsia
    Vinnytsia is a major city in central Ukraine known as an important administrative, economic, and cultural center on the Southern Bug River.
  • C. Rivne
    Rivne is a city in western Ukraine that serves as an important regional administrative, economic, and cultural center.
  • D. Hlukhiv
    Hlukhiv is a historic city in northern Ukraine that served as an important political and cultural center of the Cossack Hetmanate in the 18th century.
  • E. Khmelnytskyi
    Khmelnytskyi is a regional city in western Ukraine known as an important administrative, economic, and cultural center.
  • 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: Zhovkva
Triple: [Zamość, twinTown, Zhovkva]
Generated description
Zhovkva is a historic town in western Ukraine known for its well-preserved Renaissance architecture and multicultural heritage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Zhovkva
Target entity description: Zhovkva is a historic town in western Ukraine known for its well-preserved Renaissance architecture and multicultural heritage.
  • A. Ivano-Frankivsk
    Ivano-Frankivsk is a historic city in western Ukraine known as a cultural, economic, and administrative center of the Carpathian region.
  • B. Vinnytsia
    Vinnytsia is a major city in central Ukraine known as an important administrative, economic, and cultural center on the Southern Bug River.
  • C. Rivne
    Rivne is a city in western Ukraine that serves as an important regional administrative, economic, and cultural center.
  • D. Hlukhiv
    Hlukhiv is a historic city in northern Ukraine that served as an important political and cultural center of the Cossack Hetmanate in the 18th century.
  • E. Khmelnytskyi
    Khmelnytskyi is a regional city in western Ukraine known as an important administrative, economic, and cultural center.
  • 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_69ab4b7a85bc819094a349b84beb1f2c completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdb7073d081909da84b21015972f2 completed March 7, 2026, 8:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69b38ba5bc088190bd656c2959cdfb6a completed March 13, 2026, 3:59 a.m.
NEDg Description generation batch_69b3acb9a94c81909f6d0a3f43dc43e9 completed March 13, 2026, 6:20 a.m.
NED2 Entity disambiguation (via description) batch_69b3ad2484288190ad5c603418e984fb completed March 13, 2026, 6:22 a.m.
Created at: March 6, 2026, 9:56 p.m.