Triple

T16307453
Position Surface form Disambiguated ID Type / Status
Subject Järva County E395957 entity
Predicate containsSettlement P847 FINISHED
Object Mäeküla
Mäeküla is a small settlement located in Järva County in central Estonia.
E1206819 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: Mäeküla | Statement: [Järva County, containsSettlement, Mäeküla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mäeküla
Context triple: [Järva County, containsSettlement, Mäeküla]
  • A. Kõrgessaare
    Kõrgessaare is a small settlement on the island of Hiiumaa in western Estonia, known for its coastal location and rural character.
  • B. Kivimäe
    Kivimäe is a residential subdistrict within the Nõmme district of Tallinn, Estonia, known for its green, suburban character.
  • C. Vahuküla
    Vahuküla is a small village located in Järva County in central Estonia.
  • D. Pääsküla
    Pääsküla is a subdistrict of the Nõmme district in Tallinn, Estonia, known for its residential areas and nearby natural landscapes.
  • E. Rohuküla
    Rohuküla is a small coastal village and port on Estonia’s western coast that serves as a key mainland ferry terminal for connections to nearby islands such as Hiiumaa.
  • 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: Mäeküla
Triple: [Järva County, containsSettlement, Mäeküla]
Generated description
Mäeküla is a small settlement located in Järva County in central Estonia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mäeküla
Target entity description: Mäeküla is a small settlement located in Järva County in central Estonia.
  • A. Kõrgessaare
    Kõrgessaare is a small settlement on the island of Hiiumaa in western Estonia, known for its coastal location and rural character.
  • B. Kivimäe
    Kivimäe is a residential subdistrict within the Nõmme district of Tallinn, Estonia, known for its green, suburban character.
  • C. Vahuküla
    Vahuküla is a small village located in Järva County in central Estonia.
  • D. Pääsküla
    Pääsküla is a subdistrict of the Nõmme district in Tallinn, Estonia, known for its residential areas and nearby natural landscapes.
  • E. Rohuküla
    Rohuküla is a small coastal village and port on Estonia’s western coast that serves as a key mainland ferry terminal for connections to nearby islands such as Hiiumaa.
  • 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_69d87f23bb088190a16fbb91a1957ea5 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e288d63b688190ad5ebc3fb5dd5b4c completed April 17, 2026, 7:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00260151908190b83f700a1c7c6419 completed May 10, 2026, 6:30 a.m.
NEDg Description generation batch_6a0026b6554481909ee5a4de41293d90 completed May 10, 2026, 6:33 a.m.
NED2 Entity disambiguation (via description) batch_6a002750c490819082db2044b6a89eaa completed May 10, 2026, 6:36 a.m.
Created at: April 10, 2026, 5:06 a.m.