Triple

T14560499
Position Surface form Disambiguated ID Type / Status
Subject Royal Moroccan Air Force E341651 entity
Predicate trainingBase P11445 FINISHED
Object Marrakesh Air Base
Marrakesh Air Base is a key Royal Moroccan Air Force installation in Morocco that serves as an important hub for military aviation operations and pilot training.
E1120630 NE FINISHED

How this triple was built (4 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: Marrakesh Air Base | Statement: [Royal Moroccan Air Force, trainingBase, Marrakesh Air Base]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marrakesh Air Base
Context triple: [Royal Moroccan Air Force, trainingBase, Marrakesh Air Base]
  • A. Meknes Air Base
    Meknes Air Base is a Moroccan military airfield that serves as a key installation for the Royal Moroccan Air Force.
  • B. Kenitra Air Base
    Kenitra Air Base is a military airfield in Kenitra, Morocco, serving as a key installation of the Royal Moroccan Air Force.
  • C. Ben Guerir Air Base
    Ben Guerir Air Base is a military airfield in Morocco that serves as a key installation for the Royal Moroccan Air Force.
  • D. Sidi Slimane Air Base
    Sidi Slimane Air Base is a Moroccan military airfield used by the Royal Moroccan Air Force.
  • E. Laayoune Air Base
    Laayoune Air Base is a military airfield in Western Sahara serving as a key installation for Morocco’s Royal Air Force.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Marrakesh Air Base
Triple: [Royal Moroccan Air Force, trainingBase, Marrakesh Air Base]
Generated description
Marrakesh Air Base is a key Royal Moroccan Air Force installation in Morocco that serves as an important hub for military aviation operations and pilot training.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marrakesh Air Base
Target entity description: Marrakesh Air Base is a key Royal Moroccan Air Force installation in Morocco that serves as an important hub for military aviation operations and pilot training.
  • A. Meknes Air Base
    Meknes Air Base is a Moroccan military airfield that serves as a key installation for the Royal Moroccan Air Force.
  • B. Kenitra Air Base
    Kenitra Air Base is a military airfield in Kenitra, Morocco, serving as a key installation of the Royal Moroccan Air Force.
  • C. Ben Guerir Air Base
    Ben Guerir Air Base is a military airfield in Morocco that serves as a key installation for the Royal Moroccan Air Force.
  • D. Sidi Slimane Air Base
    Sidi Slimane Air Base is a Moroccan military airfield used by the Royal Moroccan Air Force.
  • E. Laayoune Air Base
    Laayoune Air Base is a military airfield in Western Sahara serving as a key installation for Morocco’s Royal Air Force.
  • F. None of above. chosen

Provenance (5 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_69fe24a2fc048190b68d3267fe17471b completed May 8, 2026, 6 p.m.
NEDg Description generation batch_69fe267a18348190a979d8bc26cb9740 completed May 8, 2026, 6:07 p.m.
NED2 Entity disambiguation (via description) batch_69fe26ca706881908fe0da780bd9f691 completed May 8, 2026, 6:09 p.m.
Created at: April 10, 2026, 1:23 a.m.