Triple

T20355663
Position Surface form Disambiguated ID Type / Status
Subject 23rd Flying Training Squadron E496638 entity
Predicate abbreviation P43 FINISHED
Object 23 FTS
23 FTS is a United States Air Force flying training squadron responsible for instructing and preparing pilots in specialized flight operations.
 E1426701 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: 23 FTS | Statement: [23rd Flying Training Squadron, abbreviation, 23 FTS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 23 FTS
Context triple: [23rd Flying Training Squadron, abbreviation, 23 FTS]
  • A. 3 FTS
    3 FTS is a Royal Air Force flying training unit responsible for instructing and qualifying new military pilots in the United Kingdom.
  • B. FTS
    FTS is the commonly used abbreviation for the Financial Tracking Service, a global humanitarian aid financial tracking system managed by the United Nations.
  • C. 302 TFS
    302 TFS is a designation commonly used for the 302nd Tactical Fighter Squadron, a military aviation unit equipped and trained for tactical fighter operations.
  • D. F33
    F33 is BMW’s internal designation for the first-generation 4 Series convertible model.
  • E. 325 FW
    325 FW is a United States Air Force fighter wing known for training and operating combat-ready F-22 Raptor pilots and support personnel.
  • 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: 23 FTS
Triple: [23rd Flying Training Squadron, abbreviation, 23 FTS]
Generated description
23 FTS is a United States Air Force flying training squadron responsible for instructing and preparing pilots in specialized flight operations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: 23 FTS
Target entity description: 23 FTS is a United States Air Force flying training squadron responsible for instructing and preparing pilots in specialized flight operations.
  • A. 3 FTS
    3 FTS is a Royal Air Force flying training unit responsible for instructing and qualifying new military pilots in the United Kingdom.
  • B. FTS
    FTS is the commonly used abbreviation for the Financial Tracking Service, a global humanitarian aid financial tracking system managed by the United Nations.
  • C. 302 TFS
    302 TFS is a designation commonly used for the 302nd Tactical Fighter Squadron, a military aviation unit equipped and trained for tactical fighter operations.
  • D. F33
    F33 is BMW’s internal designation for the first-generation 4 Series convertible model.
  • E. 325 FW
    325 FW is a United States Air Force fighter wing known for training and operating combat-ready F-22 Raptor pilots and support personnel.
  • 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_69e0b4a3f7f48190b37f354574028ca6 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67853f10881908ecde94036804a8a completed April 20, 2026, 7:02 p.m.
NED1 Entity disambiguation (via context triple) batch_6a087081a8d88190a0144632eab72309 completed May 16, 2026, 1:26 p.m.
NEDg Description generation batch_6a0870fd8b8c8190ac7ac5d2b0d9e8c4 completed May 16, 2026, 1:28 p.m.
NED2 Entity disambiguation (via description) batch_6a087213a0408190a9b553323d7ced1f completed May 16, 2026, 1:33 p.m.
Created at: April 16, 2026, 11:25 a.m.