Triple

T20676290
Position Surface form Disambiguated ID Type / Status
Subject KOPRI E508167 entity
Predicate abbreviation P43 FINISHED
Object KOPRI 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: KOPRI | Statement: [KOPRI, abbreviation, KOPRI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KOPRI
Context triple: [KOPRI, abbreviation, KOPRI]
  • A. KOPRI chosen
    KOPRI is South Korea’s national polar research institute, responsible for conducting and coordinating the country’s scientific activities in the Arctic and Antarctic regions.
  • B. Korea Polar Research Institute
    The Korea Polar Research Institute is South Korea’s national organization dedicated to polar science, exploration, and research infrastructure in the Arctic and Antarctic regions.
  • C. Korea Astronomy and Space Science Institute
    The Korea Astronomy and Space Science Institute is South Korea’s national research organization dedicated to astronomical observation, space science, and related technological development.
  • D. Kopri
    Kopri is a residential suburb located in the city of Thane in Maharashtra, India.
  • E. Korea Aerospace Research Institute
    The Korea Aerospace Research Institute is South Korea’s national space agency responsible for developing and managing the country’s space and aerospace technologies, including satellites and launch vehicles.
  • 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_69e0b4c1164881909a3bf1e3ddb2bc32 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b5cf18b48190be6995e197946517 completed April 20, 2026, 11:25 p.m.
Created at: April 16, 2026, 11:44 a.m.