Triple

T14560493
Position Surface form Disambiguated ID Type / Status
Subject Royal Moroccan Air Force E341651 entity
Predicate usesAircraft P1524 FINISHED
Object Heron UAV E518932 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: Heron UAV | Statement: [Royal Moroccan Air Force, usesAircraft, Heron UAV]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Heron UAV
Context triple: [Royal Moroccan Air Force, usesAircraft, Heron UAV]
  • A. Heron UAV chosen
    The Heron UAV is a medium-altitude long-endurance unmanned aerial vehicle developed by Israel Aerospace Industries, widely used for intelligence, surveillance, and reconnaissance missions.
  • B. Harfang UAV
    The Harfang UAV is a French-developed medium-altitude, long-endurance unmanned aerial vehicle designed primarily for intelligence, surveillance, and reconnaissance missions.
  • C. ANKA UAV
    ANKA UAV is a Turkish-made medium-altitude long-endurance unmanned aerial vehicle designed primarily for intelligence, surveillance, and reconnaissance missions.
  • D. DJI Agras
    DJI Agras is a series of agricultural drones designed for tasks like crop spraying, seeding, and precision farming.
  • E. RQ-7 Shadow
    The RQ-7 Shadow is a tactical unmanned aerial vehicle used by the U.S. Army for battlefield reconnaissance, surveillance, and target acquisition.
  • 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_69d822dcc6248190bed689984bceb0e2 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb389d0f48190a1d9d69456d1cbe1 completed April 14, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd94b1760481909119db555fd05429 completed May 8, 2026, 7:45 a.m.
Created at: April 10, 2026, 1:23 a.m.