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.