Triple

T9529758
Position Surface form Disambiguated ID Type / Status
Subject Matti Kekkonen E229856 entity
Predicate familyName P18 FINISHED
Object Kekkonen E823122 NE FINISHED

How this triple was built (2 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: Kekkonen | Statement: [Matti Kekkonen, familyName, Kekkonen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kekkonen
Context triple: [Matti Kekkonen, familyName, Kekkonen]
  • A. Kekkonen chosen
    Kekkonen is a Finnish surname most famously associated with Urho Kekkonen, the long-serving President of Finland.
  • B. Antero Kekkonen
    Antero Kekkonen is a Finnish politician and diplomat, known as a member of the prominent Kekkonen family that includes former President Urho Kekkonen.
  • C. Seppo Kekkonen
    Seppo Kekkonen was a Finnish lawyer and diplomat, known as the son of longtime President Urho Kekkonen and brother of diplomat Taneli Kekkonen.
  • D. Jukka Kekkonen
    Jukka Kekkonen is a Finnish legal scholar and professor known for his work in legal history and criminal law.
  • E. Urho Kekkonen
    Urho Kekkonen was a long-serving Finnish statesman who served as President of Finland from 1956 to 1982 and played a key role in shaping the country’s Cold War foreign policy.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca8479934c81908006d0e6e970ae05 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd98b2de3081909be70d9ab187dce6 completed April 1, 2026, 10:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69d28194f6e88190932efe607088394a completed April 5, 2026, 3:36 p.m.
Created at: March 30, 2026, 8 p.m.