Triple

T4316166
Position Surface form Disambiguated ID Type / Status
Subject Gaiziņkalns E96396 entity
Predicate nearSettlement P3883 FINISHED
Object Bērzaune
Bērzaune is a small settlement in Latvia located close to Gaiziņkalns, the country’s highest hill.
 E432412 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: Bērzaune | Statement: [Gaiziņkalns, nearSettlement, Bērzaune]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bērzaune
Context triple: [Gaiziņkalns, nearSettlement, Bērzaune]
  • A. Bērze
    Bērze is a river in Latvia that serves as one of the tributaries feeding into the larger Lielupe River system.
  • B. Kazlų Rūda
    Kazlų Rūda is a small town in central Lithuania known for its surrounding forests, timber industry, and railway connections.
  • C. Prasne
    Prasne is a notable literary work by renowned Indian writer U. R. Ananthamurthy, associated with modern Kannada literature.
  • D. Švenčionys
    Švenčionys is a small historic town in eastern Lithuania known for its multicultural past and former Jewish community.
  • E. Lindinis
    Lindinis is the Roman-era name for the town now known as Ilchester in Somerset, England, which served as an important settlement in Roman Britain.
  • 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: Bērzaune
Triple: [Gaiziņkalns, nearSettlement, Bērzaune]
Generated description
Bērzaune is a small settlement in Latvia located close to Gaiziņkalns, the country’s highest hill.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bērzaune
Target entity description: Bērzaune is a small settlement in Latvia located close to Gaiziņkalns, the country’s highest hill.
  • A. Bērze
    Bērze is a river in Latvia that serves as one of the tributaries feeding into the larger Lielupe River system.
  • B. Kazlų Rūda
    Kazlų Rūda is a small town in central Lithuania known for its surrounding forests, timber industry, and railway connections.
  • C. Prasne
    Prasne is a notable literary work by renowned Indian writer U. R. Ananthamurthy, associated with modern Kannada literature.
  • D. Švenčionys
    Švenčionys is a small historic town in eastern Lithuania known for its multicultural past and former Jewish community.
  • E. Lindinis
    Lindinis is the Roman-era name for the town now known as Ilchester in Somerset, England, which served as an important settlement in Roman Britain.
  • 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_69b345422aac81909ddbadae437d122e completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b350f60dfc819098202b7eb3bbf402 completed March 12, 2026, 11:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5db9193c08190a6a63b82f604ecde completed March 14, 2026, 10:05 p.m.
NEDg Description generation batch_69b5dc1eedc08190b50b72b59cf1dcf0 completed March 14, 2026, 10:07 p.m.
NED2 Entity disambiguation (via description) batch_69b5dcbf4d5081908d24bce8e2769124 completed March 14, 2026, 10:10 p.m.
Created at: March 12, 2026, 11:12 p.m.