Triple

T20543182
Position Surface form Disambiguated ID Type / Status
Subject Mir EO-20 E504397 entity
Predicate operator P179 FINISHED
Object RKA 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: RKA | Statement: [Mir EO-20, operator, RKA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RKA
Context triple: [Mir EO-20, operator, RKA]
  • A. RKA chosen
    RKA is the Russian Space Agency that managed Russia’s human spaceflight activities, including operations of the Mir space station.
  • B. RJKA
    RJKA is the ICAO airport code for Amami Airport, a regional airport serving Amami Ōshima in Kagoshima Prefecture, Japan.
  • C. RKR
    RKR is the vehicle registration code assigned to vehicles registered in the Rymanów area of Poland.
  • D. RKC
    RKC is the commonly used abbreviation for the Revised Kyoto Convention, an international agreement that standardizes and simplifies customs procedures worldwide.
  • E. RKT
    RKT is the IATA airport code for Ras Al Khaimah International Airport in the United Arab Emirates.
  • 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_69e0b4b476648190bc6019622ae54d3c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a293feac8190b27848b64f2db1fe completed April 20, 2026, 10:03 p.m.
Created at: April 16, 2026, 11:38 a.m.