Triple

T4436572
Position Surface form Disambiguated ID Type / Status
Subject Skvyra E95664 entity
Predicate nameInUkrainian P25447 FINISHED
Object Сквира
Сквира — це невелике місто в Київській області України, відоме як районний центр із переважно сільськогосподарським оточенням та історичною єврейською спадщиною.
 E440206 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: Сквира | Statement: [Skvyra, nameInUkrainian, Сквира]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Сквира
Context triple: [Skvyra, nameInUkrainian, Сквира]
  • A. Tealing
    Tealing is a small rural village in eastern Scotland, situated in the Angus council area just north of Dundee.
  • B. Dolgan
    Dolgan is a Turkic language spoken primarily by the Dolgan people in northern Siberia, especially in Russia’s Taymyr Peninsula.
  • C. Southesk
    Southesk is the traditional war cry associated with Clan Carnegie, a Scottish noble family from Angus.
  • D. Olesko
    Olesko is a historic town in western Ukraine best known for its medieval castle, which served as the birthplace of Polish King John III Sobieski.
  • E. Moura
    Moura is a small coal-mining town in Central Queensland, Australia, known for its agricultural activities and history of mining disasters.
  • 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: Сквира
Triple: [Skvyra, nameInUkrainian, Сквира]
Generated description
Сквира — це невелике місто в Київській області України, відоме як районний центр із переважно сільськогосподарським оточенням та історичною єврейською спадщиною.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Сквира
Target entity description: Сквира — це невелике місто в Київській області України, відоме як районний центр із переважно сільськогосподарським оточенням та історичною єврейською спадщиною.
  • A. Tealing
    Tealing is a small rural village in eastern Scotland, situated in the Angus council area just north of Dundee.
  • B. Dolgan
    Dolgan is a Turkic language spoken primarily by the Dolgan people in northern Siberia, especially in Russia’s Taymyr Peninsula.
  • C. Southesk
    Southesk is the traditional war cry associated with Clan Carnegie, a Scottish noble family from Angus.
  • D. Olesko
    Olesko is a historic town in western Ukraine best known for its medieval castle, which served as the birthplace of Polish King John III Sobieski.
  • E. Moura
    Moura is a small coal-mining town in Central Queensland, Australia, known for its agricultural activities and history of mining disasters.
  • 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_69b3453ea2b48190a26f154b3b8fece5 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3558b1d4481909060ede5e0ded4bc completed March 13, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69b6137960908190814cbdf0b4e56542 completed March 15, 2026, 2:03 a.m.
NEDg Description generation batch_69b61439a86c8190849c5af718ddc647 completed March 15, 2026, 2:06 a.m.
NED2 Entity disambiguation (via description) batch_69b614d6106c81908a601f540622f934 completed March 15, 2026, 2:09 a.m.
Created at: March 12, 2026, 11:31 p.m.