Triple

T4447967
Position Surface form Disambiguated ID Type / Status
Subject Principality of Polotsk E96335 entity
Predicate hasPart P35 FINISHED
Object Lukoml
Lukoml is a historic settlement in present-day Belarus that was once an important locality within the medieval East Slavic Principality of Polotsk.
E441004 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: Lukoml | Statement: [Principality of Polotsk, hasPart, Lukoml]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lukoml
Context triple: [Principality of Polotsk, hasPart, Lukoml]
  • A. Lom
    Lom is a mountainous municipality in Innlandet county, Norway, known for its historic stave church and as a gateway to the Jotunheimen National Park.
  • B. Lomu
    Lomu is a surname most famously associated with Jonah Lomu, the legendary New Zealand rugby union winger.
  • C. Lugnut
    Lugnut is the costumed mascot character for the Lansing Lugnuts minor league baseball team, entertaining fans at games and team events.
  • D. Liuboml
    Liuboml is a small historic town in western Ukraine near the Polish border, known for its medieval roots and multicultural heritage.
  • E. Lutakko
    Lutakko is a central lakeside district of Jyväskylä, Finland, known for its modern residential areas, event venues, and the annual Jyväskylä Rock Festival.
  • 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: Lukoml
Triple: [Principality of Polotsk, hasPart, Lukoml]
Generated description
Lukoml is a historic settlement in present-day Belarus that was once an important locality within the medieval East Slavic Principality of Polotsk.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lukoml
Target entity description: Lukoml is a historic settlement in present-day Belarus that was once an important locality within the medieval East Slavic Principality of Polotsk.
  • A. Lom
    Lom is a mountainous municipality in Innlandet county, Norway, known for its historic stave church and as a gateway to the Jotunheimen National Park.
  • B. Lomu
    Lomu is a surname most famously associated with Jonah Lomu, the legendary New Zealand rugby union winger.
  • C. Lugnut
    Lugnut is the costumed mascot character for the Lansing Lugnuts minor league baseball team, entertaining fans at games and team events.
  • D. Liuboml
    Liuboml is a small historic town in western Ukraine near the Polish border, known for its medieval roots and multicultural heritage.
  • E. Lutakko
    Lutakko is a central lakeside district of Jyväskylä, Finland, known for its modern residential areas, event venues, and the annual Jyväskylä Rock Festival.
  • 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_69b345415ba481908df738e7174448ba completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b355d45b748190b09b7067fc6279b0 completed March 13, 2026, 12:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69b61386df48819080e44a23b9d67d23 completed March 15, 2026, 2:03 a.m.
NEDg Description generation batch_69b617c13d4481909d22d201ce405d3a completed March 15, 2026, 2:21 a.m.
NED2 Entity disambiguation (via description) batch_69b6187687f8819084e2d611e9e31f79 completed March 15, 2026, 2:24 a.m.
Created at: March 12, 2026, 11:32 p.m.