Triple

T11922818
Position Surface form Disambiguated ID Type / Status
Subject Edward Bodden Airfield E283698 entity
Predicate ICAOcode P419 FINISHED
Object MWCL
MWCL is the ICAO airport code assigned to Edward Bodden Airfield in the Cayman Islands.
 E954699 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: MWCL | Statement: [Edward Bodden Airfield, ICAOcode, MWCL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MWCL
Context triple: [Edward Bodden Airfield, ICAOcode, MWCL]
  • A. MCWL
    MCWL is the U.S. Marine Corps Warfighting Laboratory, responsible for developing, testing, and integrating innovative concepts and technologies to enhance future Marine Corps combat capabilities.
  • B. WCL
    WCL is the commonly used abbreviation for the American University Washington College of Law, a prominent law school in Washington, D.C.
  • C. MCMWTC
    MCMWTC is a United States Marine Corps training installation in the Sierra Nevada dedicated to preparing Marines for operations in mountainous and cold-weather environments.
  • D. MCL
    MCL is a specialized postgraduate law degree at the University of Cambridge focused on corporate and commercial law.
  • E. SMCLs
    SMCLs are non-enforceable federal guidelines that recommend acceptable levels of certain contaminants in drinking water based on aesthetic factors like taste, color, and odor rather than health risks.
  • 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: MWCL
Triple: [Edward Bodden Airfield, ICAOcode, MWCL]
Generated description
MWCL is the ICAO airport code assigned to Edward Bodden Airfield in the Cayman Islands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MWCL
Target entity description: MWCL is the ICAO airport code assigned to Edward Bodden Airfield in the Cayman Islands.
  • A. MCWL
    MCWL is the U.S. Marine Corps Warfighting Laboratory, responsible for developing, testing, and integrating innovative concepts and technologies to enhance future Marine Corps combat capabilities.
  • B. WCL
    WCL is the commonly used abbreviation for the American University Washington College of Law, a prominent law school in Washington, D.C.
  • C. MCMWTC
    MCMWTC is a United States Marine Corps training installation in the Sierra Nevada dedicated to preparing Marines for operations in mountainous and cold-weather environments.
  • D. MCL
    MCL is a specialized postgraduate law degree at the University of Cambridge focused on corporate and commercial law.
  • E. SMCLs
    SMCLs are non-enforceable federal guidelines that recommend acceptable levels of certain contaminants in drinking water based on aesthetic factors like taste, color, and odor rather than health risks.
  • 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_69d6ab2ce9c48190b5d39511b524f666 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8e8e1b08481909ed291667035f330 completed April 10, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69f44042cf1c81909de44acfe1202482 completed May 1, 2026, 5:55 a.m.
NEDg Description generation batch_69f448fa8eec81909fe6ac0902f46998 completed May 1, 2026, 6:32 a.m.
NED2 Entity disambiguation (via description) batch_69f44aef15148190ba8090681b921ffa completed May 1, 2026, 6:40 a.m.
Created at: April 8, 2026, 9:45 p.m.