Triple

T20156698
Position Surface form Disambiguated ID Type / Status
Subject Taavi Rõivas E491588 entity
Predicate name P16 FINISHED
Object Taavi Rõivas NE NERFINISHED

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: Taavi Rõivas | Statement: [Taavi Rõivas, name, Taavi Rõivas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taavi Rõivas
Context triple: [Taavi Rõivas, name, Taavi Rõivas]
  • A. Taavi Rõivas chosen
    Taavi Rõivas is an Estonian politician who served as the Prime Minister of Estonia from 2014 to 2016.
  • B. Jüri Ratas
    Jüri Ratas is an Estonian politician who has served as the Prime Minister of Estonia and a leading figure in the Centre Party.
  • C. Toomas Kivimägi
    Toomas Kivimägi is an Estonian politician and lawyer who has served as a member of the Riigikogu and held prominent regional leadership roles.
  • D. Toomas Tõniste
    Toomas Tõniste is an Estonian politician and former Olympic sailor who has served as Estonia’s Minister of Finance.
  • E. Siim Kallas
    Siim Kallas is an Estonian politician and former European Commissioner who served as Estonia’s Prime Minister and played a key role in the country’s post-Soviet economic and political reforms.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667e0a0488190a25d92aaf300be4a completed April 20, 2026, 5:52 p.m.
Created at: April 11, 2026, 11:34 p.m.