Triple

T2798044
Position Surface form Disambiguated ID Type / Status
Subject Ben Shahn E53085 entity
Predicate placeOfBirth P1 FINISHED
Object Kovno
Kovno is the historical name for Kaunas, a major city in Lithuania that was once part of the Russian Empire and had a significant Jewish community.
 E301401 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: Kovno | Statement: [Ben Shahn, placeOfBirth, Kovno]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kovno
Context triple: [Ben Shahn, placeOfBirth, Kovno]
  • A. Alytus
    Alytus is a city in southern Lithuania known as a regional cultural and economic center on the banks of the Nemunas River.
  • B. Vilna
    Vilna is the historical name for Vilnius, the capital city of Lithuania and a major cultural and political center of the region.
  • C. Trakai
    Trakai is a historic Lithuanian town famed for its medieval island castle and former status as a political center of the Grand Duchy of Lithuania.
  • D. Wilno
    Wilno is the historical Polish name for Vilnius, a major cultural and political center of the region that served as an important city in the interwar Second Polish Republic.
  • E. Vilnius
    Vilnius is the capital and largest city of Lithuania, known for its well-preserved medieval Old Town and rich cultural and historical heritage.
  • 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: Kovno
Triple: [Ben Shahn, placeOfBirth, Kovno]
Generated description
Kovno is the historical name for Kaunas, a major city in Lithuania that was once part of the Russian Empire and had a significant Jewish community.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kovno
Target entity description: Kovno is the historical name for Kaunas, a major city in Lithuania that was once part of the Russian Empire and had a significant Jewish community.
  • A. Alytus
    Alytus is a city in southern Lithuania known as a regional cultural and economic center on the banks of the Nemunas River.
  • B. Vilna
    Vilna is the historical name for Vilnius, the capital city of Lithuania and a major cultural and political center of the region.
  • C. Trakai
    Trakai is a historic Lithuanian town famed for its medieval island castle and former status as a political center of the Grand Duchy of Lithuania.
  • D. Wilno
    Wilno is the historical Polish name for Vilnius, a major cultural and political center of the region that served as an important city in the interwar Second Polish Republic.
  • E. Vilnius
    Vilnius is the capital and largest city of Lithuania, known for its well-preserved medieval Old Town and rich cultural and historical heritage.
  • 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_69ab495a90788190941b6917e1eca3a6 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abddf204148190a53f3f30d645d94c completed March 7, 2026, 8:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69afce92b40c8190a6ed3e6c06f15c79 completed March 10, 2026, 7:56 a.m.
NEDg Description generation batch_69afcf3aa64081909fe4007d94df48c2 completed March 10, 2026, 7:58 a.m.
NED2 Entity disambiguation (via description) batch_69afcfe8a140819095daa37d539e4c72 completed March 10, 2026, 8:01 a.m.
Created at: March 6, 2026, 9:58 p.m.