Triple

T20231101
Position Surface form Disambiguated ID Type / Status
Subject Repovesi National Park E495525 entity
Predicate locatedIn P40 FINISHED
Object Mäntyharju
Mäntyharju is a municipality in southeastern Finland known for its forested lake landscapes and outdoor recreation opportunities.
E1418663 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: Mäntyharju | Statement: [Repovesi National Park, locatedIn, Mäntyharju]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mäntyharju
Context triple: [Repovesi National Park, locatedIn, Mäntyharju]
  • A. Koivu
    Koivu is a Finnish surname most prominently associated with former NHL players Mikko and Saku Koivu.
  • B. Martta
    Martta is a feminine given name, commonly used in Finland and other Nordic countries, that is a variant of the name Martha.
  • C. Pöytyä
    Pöytyä is a rural municipality in southwestern Finland known for its forests, agriculture, and small village communities.
  • D. Ristonmaa
    Ristonmaa is a residential district within the Kuokkala area of Jyväskylä, Finland.
  • E. Vihti
    Vihti is a municipality in southern Finland located within the Uusimaa region, known for its lakes, rural landscapes, and proximity to the Helsinki metropolitan 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: Mäntyharju
Triple: [Repovesi National Park, locatedIn, Mäntyharju]
Generated description
Mäntyharju is a municipality in southeastern Finland known for its forested lake landscapes and outdoor recreation opportunities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mäntyharju
Target entity description: Mäntyharju is a municipality in southeastern Finland known for its forested lake landscapes and outdoor recreation opportunities.
  • A. Koivu
    Koivu is a Finnish surname most prominently associated with former NHL players Mikko and Saku Koivu.
  • B. Martta
    Martta is a feminine given name, commonly used in Finland and other Nordic countries, that is a variant of the name Martha.
  • C. Pöytyä
    Pöytyä is a rural municipality in southwestern Finland known for its forests, agriculture, and small village communities.
  • D. Ristonmaa
    Ristonmaa is a residential district within the Kuokkala area of Jyväskylä, Finland.
  • E. Vihti
    Vihti is a municipality in southern Finland located within the Uusimaa region, known for its lakes, rural landscapes, and proximity to the Helsinki metropolitan 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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66fdce9d081909752a6a1e15283ba completed April 20, 2026, 6:26 p.m.
NED1 Entity disambiguation (via context triple) batch_6a084b8c7c9881908f724d10c915963a completed May 16, 2026, 10:48 a.m.
NEDg Description generation batch_6a084c041b5c8190881a6d08c4afe42f completed May 16, 2026, 10:50 a.m.
NED2 Entity disambiguation (via description) batch_6a084c7dee808190a0883f7f0c7873a9 completed May 16, 2026, 10:52 a.m.
Created at: April 11, 2026, 11:39 p.m.