Triple

T6746618
Position Surface form Disambiguated ID Type / Status
Subject Latgale E154233 entity
Predicate borders P224 FINISHED
Object Sēlija
Sēlija is a historical and cultural region in southeastern Latvia known for its rural landscapes, traditional wooden architecture, and distinct Selonian heritage.
 E615717 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: Sēlija | Statement: [Latgale, borders, Sēlija]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sēlija
Context triple: [Latgale, borders, Sēlija]
  • A. Suleja
    Suleja is a town in Niger State, Nigeria, located near the capital Abuja and known as a key gateway between the capital region and the country’s northwestern areas.
  • B. Dausa
    Dausa is a town and district headquarters in the Indian state of Rajasthan, known for its historical forts, stepwells, and proximity to Jaipur.
  • C. Sosva
    Sosva is a rural locality in Sverdlovsk Oblast, Russia, historically known as the site of a Soviet-era labor camp where Finnish communist leader Kullervo Manner died.
  • D. Salacia
    Salacia is the Roman goddess of the sea, particularly associated with saltwater and often regarded as the consort of Neptune.
  • E. Sila
    Sila is a mountainous plateau in Calabria, southern Italy, known for its dense forests, lakes, and national park.
  • 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: Sēlija
Triple: [Latgale, borders, Sēlija]
Generated description
Sēlija is a historical and cultural region in southeastern Latvia known for its rural landscapes, traditional wooden architecture, and distinct Selonian heritage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sēlija
Target entity description: Sēlija is a historical and cultural region in southeastern Latvia known for its rural landscapes, traditional wooden architecture, and distinct Selonian heritage.
  • A. Suleja
    Suleja is a town in Niger State, Nigeria, located near the capital Abuja and known as a key gateway between the capital region and the country’s northwestern areas.
  • B. Dausa
    Dausa is a town and district headquarters in the Indian state of Rajasthan, known for its historical forts, stepwells, and proximity to Jaipur.
  • C. Sosva
    Sosva is a rural locality in Sverdlovsk Oblast, Russia, historically known as the site of a Soviet-era labor camp where Finnish communist leader Kullervo Manner died.
  • D. Salacia
    Salacia is the Roman goddess of the sea, particularly associated with saltwater and often regarded as the consort of Neptune.
  • E. Sila
    Sila is a mountainous plateau in Calabria, southern Italy, known for its dense forests, lakes, and national park.
  • 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_69c6880ef37881909268a5a7299b9293 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d1b8a0f0819086b802983e8ffcb6 completed March 27, 2026, 6:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69c70b15ded88190a36fb86093ba5a3c completed March 27, 2026, 10:56 p.m.
NEDg Description generation batch_69c70c334a90819084bb0b25bbc112cc completed March 27, 2026, 11:01 p.m.
NED2 Entity disambiguation (via description) batch_69c70d0fcbc08190b3a7d0de3c634a5f completed March 27, 2026, 11:04 p.m.
Created at: March 27, 2026, 2:10 p.m.