Triple

T20250902
Position Surface form Disambiguated ID Type / Status
Subject Air Wisconsin E498551 entity
Predicate ICAOCode P419 FINISHED
Object AWI
AWI is the ICAO airline designator used to identify Air Wisconsin, a regional airline in the United States.
 E1421238 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: AWI | Statement: [Air Wisconsin, ICAOCode, AWI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AWI
Context triple: [Air Wisconsin, ICAOCode, AWI]
  • A. AWI Labs
    AWI Labs is a technology company established by entrepreneur Anthony Wood, best known as the founder of Roku.
  • B. AWAE
    AWAE (Advanced Web Attacks and Exploitation) is an advanced web application penetration testing and exploitation course focused on teaching in-depth offensive security techniques to experienced security professionals.
  • C. awa
    awa is the ISO 639-3 code for Awadhi, an Indo-Aryan language spoken primarily in northern India and parts of Nepal.
  • D. AW
    AW is a German vehicle registration code associated with the district that includes the town of Remagen in the state of Rhineland-Palatinate.
  • E. AW
    AW is the standard abbreviation for Atlantic Water, the relatively warm, salty water mass originating in the North Atlantic that influences ocean circulation and Arctic climate.
  • 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: AWI
Triple: [Air Wisconsin, ICAOCode, AWI]
Generated description
AWI is the ICAO airline designator used to identify Air Wisconsin, a regional airline in the United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AWI
Target entity description: AWI is the ICAO airline designator used to identify Air Wisconsin, a regional airline in the United States.
  • A. AWI Labs
    AWI Labs is a technology company established by entrepreneur Anthony Wood, best known as the founder of Roku.
  • B. AWAE
    AWAE (Advanced Web Attacks and Exploitation) is an advanced web application penetration testing and exploitation course focused on teaching in-depth offensive security techniques to experienced security professionals.
  • C. awa
    awa is the ISO 639-3 code for Awadhi, an Indo-Aryan language spoken primarily in northern India and parts of Nepal.
  • D. AW
    AW is a German vehicle registration code associated with the district that includes the town of Remagen in the state of Rhineland-Palatinate.
  • E. AW
    AW is the standard abbreviation for Atlantic Water, the relatively warm, salty water mass originating in the North Atlantic that influences ocean circulation and Arctic climate.
  • 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_69da6274c58c81909c646eabed6f4f30 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e673a79a208190a5a7c0f6515bc393 completed April 20, 2026, 6:42 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0855262c548190b5f6102b4e6e01a6 completed May 16, 2026, 11:29 a.m.
NEDg Description generation batch_6a0856ac50e081909c8bc737e4fe6e56 completed May 16, 2026, 11:36 a.m.
NED2 Entity disambiguation (via description) batch_6a085746f2f08190a703a832f5867c7b completed May 16, 2026, 11:38 a.m.
Created at: April 11, 2026, 11:41 p.m.