Triple

T13038371
Position Surface form Disambiguated ID Type / Status
Subject Swedish Air Force F 21 Wing E326624 entity
Predicate militaryDesignation P7137 FINISHED
Object F 21
F 21 is a wing of the Swedish Air Force known for operating fighter aircraft and conducting air defense and training missions in northern Sweden.
E1018693 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: F 21 | Statement: [Swedish Air Force F 21 Wing, militaryDesignation, F 21]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: F 21
Context triple: [Swedish Air Force F 21 Wing, militaryDesignation, F 21]
  • A. F-2
    F-2 is a three-quarter-ton model in Ford’s first-generation postwar F-Series pickup truck lineup, positioned between the lighter F-1 and heavier F-3 trucks.
  • B. F-11
    F-11 is the station code assigned to Nishi-Waseda Station on Tokyo Metro’s Fukutoshin Line in Tokyo, Japan.
  • C. F-12
    F-12 is the station code assigned to Higashi-Shinjuku Station on Tokyo’s subway network.
  • D. F.2
    The F.2 is a variant of the British Supermarine Swift jet fighter, distinguished by its early service in the Royal Air Force during the 1950s.
  • E. F1–F22
    F1–F22 is a group of passenger boarding gates located in Terminal 3 of San Francisco International Airport.
  • 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: F 21
Triple: [Swedish Air Force F 21 Wing, militaryDesignation, F 21]
Generated description
F 21 is a wing of the Swedish Air Force known for operating fighter aircraft and conducting air defense and training missions in northern Sweden.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: F 21
Target entity description: F 21 is a wing of the Swedish Air Force known for operating fighter aircraft and conducting air defense and training missions in northern Sweden.
  • A. F-2
    F-2 is a three-quarter-ton model in Ford’s first-generation postwar F-Series pickup truck lineup, positioned between the lighter F-1 and heavier F-3 trucks.
  • B. F-11
    F-11 is the station code assigned to Nishi-Waseda Station on Tokyo Metro’s Fukutoshin Line in Tokyo, Japan.
  • C. F-12
    F-12 is the station code assigned to Higashi-Shinjuku Station on Tokyo’s subway network.
  • D. F.2
    The F.2 is a variant of the British Supermarine Swift jet fighter, distinguished by its early service in the Royal Air Force during the 1950s.
  • E. F1–F22
    F1–F22 is a group of passenger boarding gates located in Terminal 3 of San Francisco International Airport.
  • 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_69d8076cc45c81908123123f43e69266 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d9804b743c8190810dc5c14bc6d912 completed April 10, 2026, 10:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6cbd12eec81908ad5dae638c2210e completed May 3, 2026, 4:15 a.m.
NEDg Description generation batch_69f6cdc285788190a05a51295306f087 completed May 3, 2026, 4:23 a.m.
NED2 Entity disambiguation (via description) batch_69f6ceafcca88190bcd65be3c4440987 completed May 3, 2026, 4:27 a.m.
Created at: April 9, 2026, 8:55 p.m.