Triple

T21277045
Position Surface form Disambiguated ID Type / Status
Subject Edgar Savisaar E524414 entity
Predicate memberOf P10 FINISHED
Object Riigikogu 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: Riigikogu | Statement: [Edgar Savisaar, memberOf, Riigikogu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Riigikogu
Context triple: [Edgar Savisaar, memberOf, Riigikogu]
  • A. Riigikogu chosen
    Riigikogu is the unicameral national parliament of Estonia, responsible for enacting laws, approving the budget, and overseeing the government.
  • B. Seimas
    The Seimas is the unicameral national parliament of Lithuania, responsible for making laws, approving the government, and overseeing state affairs.
  • C. Saeima
    Saeima is the unicameral national parliament of Latvia, responsible for making laws, approving the government, and overseeing state affairs.
  • D. Parliament of Estonia
    The Parliament of Estonia is the unicameral national legislature of Estonia, responsible for enacting laws, approving the budget, and overseeing the government.
  • E. Parliament of Finland
    The Parliament of Finland is the country’s unicameral national legislature, holding supreme legislative authority and overseeing the actions of the Finnish government.
  • 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_69e0b516293c819089458ea2ec85f85e completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e736583c08819087a4726538e703e2 completed April 21, 2026, 8:33 a.m.
Created at: April 16, 2026, 4:02 p.m.