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.