Triple

T19956015
Position Surface form Disambiguated ID Type / Status
Subject Estonian Olympic Committee E479683 entity
Predicate shortName P43 FINISHED
Object EOK 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: EOK | Statement: [Estonian Olympic Committee, shortName, EOK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: EOK
Context triple: [Estonian Olympic Committee, shortName, EOK]
  • A. EOK chosen
    EOK is the Estonian Olympic Committee, the national body responsible for organizing Estonia’s participation in the Olympic Games and promoting Olympic sports in the country.
  • B. OEK
    OEK is the commonly used abbreviation for the Palau National Congress, the bicameral legislative body of the Republic of Palau.
  • C. OKE
    OKE is Oracle’s managed Kubernetes service that automates deployment, scaling, and management of containerized applications in the Oracle Cloud.
  • D. OKE
    OKE is the National Rail station code for Okehampton railway station in Devon, England.
  • E. OKO
    OKO is the IATA airport code for Yokota Air Base, a United States Air Force installation in western Tokyo, Japan.
  • 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_69d8e523c19881909f9197037200dde6 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65aefd9488190b8cdfa8543db8d31 completed April 20, 2026, 4:57 p.m.
Created at: April 10, 2026, 1:54 p.m.