Triple

T16307421
Position Surface form Disambiguated ID Type / Status
Subject Järva County E395957 entity
Predicate containsSettlement P847 FINISHED
Object Järva-Jaani
Järva-Jaani is a small town in central Estonia known for its historic wooden architecture and rural cultural heritage.
 E1205508 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: Järva-Jaani | Statement: [Järva County, containsSettlement, Järva-Jaani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Järva-Jaani
Context triple: [Järva County, containsSettlement, Järva-Jaani]
  • A. Järvi
    Järvi is a Finnish surname most prominently associated with the renowned family of conductors, including Paavo Järvi.
  • B. Järveotsa
    Järveotsa is a residential subdistrict of the Mustamäe district in Tallinn, Estonia.
  • C. Jõgõperä
    Jõgõperä is a traditional village area historically inhabited by speakers of the Votic language in Ingria.
  • D. Jõepere
    Jõepere is a village in Estonia known as the birthplace of the national writer Friedrich Reinhold Kreutzwald.
  • E. Summajärvi
    Summajärvi is a lake on the Karelian Isthmus in present-day Russia, historically associated with the nearby village of Summa and the Winter War battles fought in the area.
  • 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: Järva-Jaani
Triple: [Järva County, containsSettlement, Järva-Jaani]
Generated description
Järva-Jaani is a small town in central Estonia known for its historic wooden architecture and rural cultural heritage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Järva-Jaani
Target entity description: Järva-Jaani is a small town in central Estonia known for its historic wooden architecture and rural cultural heritage.
  • A. Järvi
    Järvi is a Finnish surname most prominently associated with the renowned family of conductors, including Paavo Järvi.
  • B. Järveotsa
    Järveotsa is a residential subdistrict of the Mustamäe district in Tallinn, Estonia.
  • C. Jõgõperä
    Jõgõperä is a traditional village area historically inhabited by speakers of the Votic language in Ingria.
  • D. Jõepere
    Jõepere is a village in Estonia known as the birthplace of the national writer Friedrich Reinhold Kreutzwald.
  • E. Summajärvi
    Summajärvi is a lake on the Karelian Isthmus in present-day Russia, historically associated with the nearby village of Summa and the Winter War battles fought in the area.
  • 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_6a001fa3353c8190825b31854a97220c completed May 10, 2026, 6:03 a.m.
NEDg Description generation batch_6a0020e282888190bb1d23b4876b4b75 completed May 10, 2026, 6:08 a.m.
NED2 Entity disambiguation (via description) batch_6a0021ba49808190bf69c22bc5c8d4da completed May 10, 2026, 6:12 a.m.
Created at: April 10, 2026, 5:06 a.m.