Triple

T11370994
Position Surface form Disambiguated ID Type / Status
Subject Garðabær E269339 entity
Predicate hasTwinTown P919 FINISHED
Object Jõhvi
Jõhvi is a town in northeastern Estonia that serves as the administrative center of Ida-Viru County.
 E921859 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: Jõhvi | Statement: [Garðabær, hasTwinTown, Jõhvi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Jõhvi
Context triple: [Garðabær, hasTwinTown, Jõhvi]
  • A. Põlva
    Põlva is a small town in southeastern Estonia known as a local administrative and cultural center surrounded by lakes and forested landscapes.
  • B. Jõgeva
    Jõgeva is a small town in eastern Estonia known as a local administrative and cultural center and for recording some of the country’s lowest winter temperatures.
  • C. Pärnamäe
    Pärnamäe is a village located in Viimsi Parish in northern Estonia, near the capital city Tallinn.
  • D. Nõmme
    Nõmme is a leafy, villa-filled suburban district of Tallinn known for its pine forests, wooden architecture, and small-town atmosphere within the capital.
  • E. Kuressaare
    Kuressaare is the main town on Estonia’s Saaremaa island, known for its well-preserved medieval castle and seaside spa resort atmosphere.
  • 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: Jõhvi
Triple: [Garðabær, hasTwinTown, Jõhvi]
Generated description
Jõhvi is a town in northeastern Estonia that serves as the administrative center of Ida-Viru County.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Jõhvi
Target entity description: Jõhvi is a town in northeastern Estonia that serves as the administrative center of Ida-Viru County.
  • A. Põlva
    Põlva is a small town in southeastern Estonia known as a local administrative and cultural center surrounded by lakes and forested landscapes.
  • B. Jõgeva
    Jõgeva is a small town in eastern Estonia known as a local administrative and cultural center and for recording some of the country’s lowest winter temperatures.
  • C. Pärnamäe
    Pärnamäe is a village located in Viimsi Parish in northern Estonia, near the capital city Tallinn.
  • D. Nõmme
    Nõmme is a leafy, villa-filled suburban district of Tallinn known for its pine forests, wooden architecture, and small-town atmosphere within the capital.
  • E. Kuressaare
    Kuressaare is the main town on Estonia’s Saaremaa island, known for its well-preserved medieval castle and seaside spa resort atmosphere.
  • 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_69d6aacca1048190b39dbbc2174616fa completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7ea8b196881909af9b138661e816d completed April 9, 2026, 6:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5568516a481909ea66cbe53968e84 completed April 19, 2026, 10:26 p.m.
NEDg Description generation batch_69e562c7de3c8190befb6d7131129a2c completed April 19, 2026, 11:18 p.m.
NED2 Entity disambiguation (via description) batch_69e56a776390819082d47ad00cf1862b completed April 19, 2026, 11:51 p.m.
Created at: April 8, 2026, 9:33 p.m.