Triple

T20382077
Position Surface form Disambiguated ID Type / Status
Subject Lääne-Harju Parish E497859 entity
Predicate contains P35 FINISHED
Object Harju-Risti
Harju-Risti is a small village in northern Estonia known for its historic medieval church and rural surroundings.
E1428264 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: Harju-Risti | Statement: [Lääne-Harju Parish, contains, Harju-Risti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harju-Risti
Context triple: [Lääne-Harju Parish, contains, Harju-Risti]
  • A. Harju
    Harju is a famous spectator-friendly city-stage in Jyväskylä that serves as one of the most iconic and crowd-drawing special stages of Rally Finland.
  • B. Harjavalta
    Harjavalta is a small industrial town and municipality in western Finland known for its metal and chemical industries along the Kokemäki River.
  • C. Harjola
    Harjola is a Finnish surname, notably borne by film director Renny Harlin (born Lauri Mauritz Harjola).
  • D. Turunmaa
    Turunmaa is the Finnish name for the Turku archipelago region in southwestern Finland, known for its numerous islands and coastal landscapes.
  • E. Koillismaa
    Koillismaa is a sparsely populated region in northeastern Finland known for its forests, lakes, and outdoor recreation opportunities.
  • 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: Harju-Risti
Triple: [Lääne-Harju Parish, contains, Harju-Risti]
Generated description
Harju-Risti is a small village in northern Estonia known for its historic medieval church and rural surroundings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Harju-Risti
Target entity description: Harju-Risti is a small village in northern Estonia known for its historic medieval church and rural surroundings.
  • A. Harju
    Harju is a famous spectator-friendly city-stage in Jyväskylä that serves as one of the most iconic and crowd-drawing special stages of Rally Finland.
  • B. Harjavalta
    Harjavalta is a small industrial town and municipality in western Finland known for its metal and chemical industries along the Kokemäki River.
  • C. Harjola
    Harjola is a Finnish surname, notably borne by film director Renny Harlin (born Lauri Mauritz Harjola).
  • D. Turunmaa
    Turunmaa is the Finnish name for the Turku archipelago region in southwestern Finland, known for its numerous islands and coastal landscapes.
  • E. Koillismaa
    Koillismaa is a sparsely populated region in northeastern Finland known for its forests, lakes, and outdoor recreation opportunities.
  • 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_69e0b4a5b7908190a972e4e7e698ae94 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e678b0ee708190bdbe4aab28a61525 completed April 20, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a087614b27c8190b5507fc1f2ef2891 completed May 16, 2026, 1:50 p.m.
NEDg Description generation batch_6a08778ad444819094ab2194a97091bd completed May 16, 2026, 1:56 p.m.
NED2 Entity disambiguation (via description) batch_6a08786c55cc81909d7195602f483d13 completed May 16, 2026, 2 p.m.
Created at: April 16, 2026, 11:27 a.m.