Triple

T22679644
Position Surface form Disambiguated ID Type / Status
Subject Hiiumaa Parish E560442 entity
Predicate containsSettlement P847 FINISHED
Object Tammela
Tammela is a small settlement located within Hiiumaa Parish on the Estonian island of Hiiumaa.
 E1554437 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: Tammela | Statement: [Hiiumaa Parish, containsSettlement, Tammela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tammela
Context triple: [Hiiumaa Parish, containsSettlement, Tammela]
  • A. Tammela
    Tammela is a rural municipality in southern Finland known for its forests, lakes, and national parks such as Torronsuo and Liesjärvi.
  • B. Tampella
    Tampella was a Finnish heavy industry company known for manufacturing machinery, armaments, and other industrial products.
  • C. Tammerkoski
    Tammerkoski is a rapid-flowing channel in Tampere, Finland, that connects two lakes and historically powered the city’s industrial development.
  • D. Terjola
    Terjola is a small city in western Georgia known for its location in the Imereti region and its surrounding wine-producing areas.
  • E. Kangasala
    Kangasala is a Finnish town and municipality in the Pirkanmaa region, known for its scenic ridge landscapes and lakes.
  • 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: Tammela
Triple: [Hiiumaa Parish, containsSettlement, Tammela]
Generated description
Tammela is a small settlement located within Hiiumaa Parish on the Estonian island of Hiiumaa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tammela
Target entity description: Tammela is a small settlement located within Hiiumaa Parish on the Estonian island of Hiiumaa.
  • A. Tammela
    Tammela is a rural municipality in southern Finland known for its forests, lakes, and national parks such as Torronsuo and Liesjärvi.
  • B. Tampella
    Tampella was a Finnish heavy industry company known for manufacturing machinery, armaments, and other industrial products.
  • C. Tammerkoski
    Tammerkoski is a rapid-flowing channel in Tampere, Finland, that connects two lakes and historically powered the city’s industrial development.
  • D. Terjola
    Terjola is a small city in western Georgia known for its location in the Imereti region and its surrounding wine-producing areas.
  • E. Kangasala
    Kangasala is a Finnish town and municipality in the Pirkanmaa region, known for its scenic ridge landscapes and lakes.
  • 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_69e2454bfd00819099115715a22cb057 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1785f68b4819082c5570f741f5135 completed April 29, 2026, 3:17 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b9e8069108190a2f8038b3e93c6e7 completed May 18, 2026, 11:19 p.m.
NEDg Description generation batch_6a0b9f4e57588190bd2f3384e431de48 completed May 18, 2026, 11:22 p.m.
NED2 Entity disambiguation (via description) batch_6a0b9fa0bf9481909e36723646eee750 completed May 18, 2026, 11:24 p.m.
Created at: April 17, 2026, 3:11 p.m.