Triple

T9087184
Position Surface form Disambiguated ID Type / Status
Subject Hlukhiv E217787 entity
Predicate nearbyCity P350 FINISHED
Object Shostka
Shostka is a city in northern Ukraine’s Sumy Oblast, historically known as an important center of the chemical and munitions industry.
 E777363 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: Shostka | Statement: [Hlukhiv, nearbyCity, Shostka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Shostka
Context triple: [Hlukhiv, nearbyCity, Shostka]
  • A. Borodin
    Borodin is a Russian surname most famously associated with Alexander Borodin, the 19th-century composer and chemist of the nationalist group known as "The Mighty Handful."
  • B. Tsitska
    Tsitska is a Georgian white grape variety from the Imereti region, known for producing fresh, high-acidity wines often used in both still and sparkling styles.
  • C. Artyomovsky
    Artyomovsky is a town in Russia’s Ural region known for its industrial base and role as a local administrative center.
  • D. Grusinskaya
    Grusinskaya is a fading but still celebrated Russian ballerina whose loneliness and vulnerability are central to the drama of the film "Grand Hotel."
  • E. Oreshek
    Oreshek is the historic Russian fortress on Lake Ladoga that later gave rise to the town of Shlisselburg.
  • 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: Shostka
Triple: [Hlukhiv, nearbyCity, Shostka]
Generated description
Shostka is a city in northern Ukraine’s Sumy Oblast, historically known as an important center of the chemical and munitions industry.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Shostka
Target entity description: Shostka is a city in northern Ukraine’s Sumy Oblast, historically known as an important center of the chemical and munitions industry.
  • A. Borodin
    Borodin is a Russian surname most famously associated with Alexander Borodin, the 19th-century composer and chemist of the nationalist group known as "The Mighty Handful."
  • B. Tsitska
    Tsitska is a Georgian white grape variety from the Imereti region, known for producing fresh, high-acidity wines often used in both still and sparkling styles.
  • C. Artyomovsky
    Artyomovsky is a town in Russia’s Ural region known for its industrial base and role as a local administrative center.
  • D. Grusinskaya
    Grusinskaya is a fading but still celebrated Russian ballerina whose loneliness and vulnerability are central to the drama of the film "Grand Hotel."
  • E. Oreshek
    Oreshek is the historic Russian fortress on Lake Ladoga that later gave rise to the town of Shlisselburg.
  • 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_69ca83d8ab5881909d8fddae363b32b1 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc965646408190b041ab0e2d5dbc94 completed April 1, 2026, 3:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69d017c893fc819087d18db2383b9bb4 completed April 3, 2026, 7:40 p.m.
NEDg Description generation batch_69d01908d7b08190ab159048f25924d5 completed April 3, 2026, 7:46 p.m.
NED2 Entity disambiguation (via description) batch_69d019b9be10819091e25d5b3a8d26c1 completed April 3, 2026, 7:49 p.m.
Created at: March 30, 2026, 7:13 p.m.