Triple

T8386832
Position Surface form Disambiguated ID Type / Status
Subject Cuban Air Force E197836 entity
Predicate usedAircraft P1524 FINISHED
Object Mi-24 E30655 NE FINISHED

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: Mi-24 | Statement: [Cuban Air Force, usedAircraft, Mi-24]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mi-24
Context triple: [Cuban Air Force, usedAircraft, Mi-24]
  • A. Mi-24 chosen
    The Mi-24 is a Soviet-designed attack helicopter and low-capacity troop transport, widely used for close air support and battlefield assault missions.
  • B. Mil Mi-34
    The Mil Mi-34 is a light, piston-engined Russian helicopter used primarily for training, sport flying, and utility roles.
  • C. Mil Mi-28
    The Mil Mi-28 is a Russian all-weather, day-night attack helicopter developed as a dedicated anti-armor platform comparable to the American AH-64 Apache.
  • D. Mil Mi-14
    The Mil Mi-14 is a Soviet amphibious anti-submarine and search-and-rescue helicopter developed from the Mi-8 and used primarily by naval aviation forces.
  • E. Mi-17
    The Mi-17 is a Russian-designed, medium-lift military transport helicopter widely used for troop transport, cargo missions, and search-and-rescue operations.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca82f749388190bffbea6dfb509016 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb81076eac8190893813628cacc1aa completed March 31, 2026, 8:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce1d1ffa988190a7b0a6b1017e144d completed April 2, 2026, 7:39 a.m.
Created at: March 30, 2026, 6:03 p.m.