Triple

T1737530
Position Surface form Disambiguated ID Type / Status
Subject Volyn Oblast E37952 entity
Predicate containsTown P847 FINISHED
Object Liuboml
Liuboml is a small historic town in western Ukraine near the Polish border, known for its medieval roots and multicultural heritage.
 E193369 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: Liuboml | Statement: [Volyn Oblast, containsTown, Liuboml]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Liuboml
Context triple: [Volyn Oblast, containsTown, Liuboml]
  • A. Antoshka
    Antoshka is a common Russian diminutive form of the male given name Anton, often used affectionately or informally.
  • 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. Yunaska
    Yunaska is the maiden surname of Lara Trump, who is married to Eric Trump, son of former U.S. President Donald Trump.
  • D. Mila
    Mila is a leading artificial intelligence research institute based in Quebec, renowned for its work in deep learning and machine learning.
  • E. Shkrebneva
    Shkrebneva is the maiden surname of Lyudmila Putina, the former wife of Russian president Vladimir Putin.
  • 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: Liuboml
Triple: [Volyn Oblast, containsTown, Liuboml]
Generated description
Liuboml is a small historic town in western Ukraine near the Polish border, known for its medieval roots and multicultural heritage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Liuboml
Target entity description: Liuboml is a small historic town in western Ukraine near the Polish border, known for its medieval roots and multicultural heritage.
  • A. Antoshka
    Antoshka is a common Russian diminutive form of the male given name Anton, often used affectionately or informally.
  • 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. Yunaska
    Yunaska is the maiden surname of Lara Trump, who is married to Eric Trump, son of former U.S. President Donald Trump.
  • D. Mila
    Mila is a leading artificial intelligence research institute based in Quebec, renowned for its work in deep learning and machine learning.
  • E. Shkrebneva
    Shkrebneva is the maiden surname of Lyudmila Putina, the former wife of Russian president Vladimir Putin.
  • 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_69a8861cc6ac8190ac0b2e31ccf62851 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa63a47cd481909c211e4da7f5dfe9 completed March 6, 2026, 5:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad8b03303c8190a301dca327bf9f47 completed March 8, 2026, 2:43 p.m.
NEDg Description generation batch_69ad957e9a6c81909d52bf2def797526 completed March 8, 2026, 3:27 p.m.
NED2 Entity disambiguation (via description) batch_69ad97b6c03881909f278594e800c0f5 completed March 8, 2026, 3:37 p.m.
Created at: March 4, 2026, 7:30 p.m.