Triple

T10751507
Position Surface form Disambiguated ID Type / Status
Subject Estonian Defence League E253581 entity
Predicate abbreviation P43 FINISHED
Object Kaitseliit
Kaitseliit is Estonia’s volunteer national defense organization that supports the country’s military and civil defense through trained reservists and local units.
E884041 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: Kaitseliit | Statement: [Estonian Defence League, abbreviation, Kaitseliit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kaitseliit
Context triple: [Estonian Defence League, abbreviation, Kaitseliit]
  • A. Ojakkala
    Ojakkala is a village in the municipality of Vihti in southern Finland, known for its rural residential character and proximity to the Helsinki metropolitan area.
  • B. Kerketeus
    Kerketeus is the ancient or alternative name for Mount Kerkis, a prominent mountain on the Greek island of Samos.
  • C. Ikaalinen
    Ikaalinen is a small town and municipality in the Pirkanmaa region of western Finland, known for its spa traditions and lakeside scenery.
  • D. Kyösti
    Kyösti is a Finnish masculine given name, notably borne by Kyösti Kallio, the fourth President of Finland.
  • E. Nellallitea
    Nellallitea is the birth name of Nella Larsen, the influential Harlem Renaissance novelist and short story writer known for exploring race and identity.
  • 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: Kaitseliit
Triple: [Estonian Defence League, abbreviation, Kaitseliit]
Generated description
Kaitseliit is Estonia’s volunteer national defense organization that supports the country’s military and civil defense through trained reservists and local units.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kaitseliit
Target entity description: Kaitseliit is Estonia’s volunteer national defense organization that supports the country’s military and civil defense through trained reservists and local units.
  • A. Ojakkala
    Ojakkala is a village in the municipality of Vihti in southern Finland, known for its rural residential character and proximity to the Helsinki metropolitan area.
  • B. Kerketeus
    Kerketeus is the ancient or alternative name for Mount Kerkis, a prominent mountain on the Greek island of Samos.
  • C. Ikaalinen
    Ikaalinen is a small town and municipality in the Pirkanmaa region of western Finland, known for its spa traditions and lakeside scenery.
  • D. Kyösti
    Kyösti is a Finnish masculine given name, notably borne by Kyösti Kallio, the fourth President of Finland.
  • E. Nellallitea
    Nellallitea is the birth name of Nella Larsen, the influential Harlem Renaissance novelist and short story writer known for exploring race and identity.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d71dc0ad188190b747bf9d10cf5de5 completed April 9, 2026, 3:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69de23292f8c8190a52c94c03e7d476d completed April 14, 2026, 11:21 a.m.
NEDg Description generation batch_69de271e2698819093bba748a0a0db5d completed April 14, 2026, 11:38 a.m.
NED2 Entity disambiguation (via description) batch_69de2cdd79608190bad8045939556bc7 completed April 14, 2026, 12:02 p.m.
Created at: April 8, 2026, 9:15 p.m.