Triple

T12908088
Position Surface form Disambiguated ID Type / Status
Subject Gomel Region E308778 entity
Predicate containsCity P294 FINISHED
Object Yelsk
Yelsk is a small town in southeastern Belarus known for its location near the Pripyat River and the border with Ukraine.
 E1014607 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: Yelsk | Statement: [Gomel Region, containsCity, Yelsk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Yelsk
Context triple: [Gomel Region, containsCity, Yelsk]
  • A. Yazhelbitsy
    Yazhelbitsy is a rural locality in Russia known for its proximity to Mount Uzhin.
  • B. Yeysk
    Yeysk is a Russian port town and resort on the Sea of Azov, known for its beaches, shallow waters, and role as a regional fishing and shipping center.
  • C. Yamskaya
    Yamskaya is a name element associated with several historic streets and districts in Moscow, traditionally linked to coachmen’s settlements along major travel routes.
  • D. Olenka
    Olenka is a Slavic diminutive form of the female given name Olga, often used as an affectionate or familiar nickname.
  • E. Grusinskaya
    Grusinskaya is a fading but still celebrated Russian ballerina whose loneliness and vulnerability are central to the drama of the film "Grand Hotel."
  • 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: Yelsk
Triple: [Gomel Region, containsCity, Yelsk]
Generated description
Yelsk is a small town in southeastern Belarus known for its location near the Pripyat River and the border with Ukraine.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Yelsk
Target entity description: Yelsk is a small town in southeastern Belarus known for its location near the Pripyat River and the border with Ukraine.
  • A. Yazhelbitsy
    Yazhelbitsy is a rural locality in Russia known for its proximity to Mount Uzhin.
  • B. Yeysk
    Yeysk is a Russian port town and resort on the Sea of Azov, known for its beaches, shallow waters, and role as a regional fishing and shipping center.
  • C. Yamskaya
    Yamskaya is a name element associated with several historic streets and districts in Moscow, traditionally linked to coachmen’s settlements along major travel routes.
  • D. Olenka
    Olenka is a Slavic diminutive form of the female given name Olga, often used as an affectionate or familiar nickname.
  • E. Grusinskaya
    Grusinskaya is a fading but still celebrated Russian ballerina whose loneliness and vulnerability are central to the drama of the film "Grand Hotel."
  • 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_69d7bdf92b588190acdf2a2291ac4590 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9719d4d1c8190a2c4f362e1772a73 completed April 10, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8d101e08190b31d6aaaecf96507 completed May 3, 2026, 2:54 a.m.
NEDg Description generation batch_69f6bcf694408190abf5e0f27e538fa7 completed May 3, 2026, 3:11 a.m.
NED2 Entity disambiguation (via description) batch_69f6bdb589248190b1a111eb5655dd19 completed May 3, 2026, 3:15 a.m.
Created at: April 9, 2026, 5:41 p.m.