Triple

T4126126
Position Surface form Disambiguated ID Type / Status
Subject MacDill Air Force Base E92728 entity
Predicate hasIATAAirportCode P2569 FINISHED
Object MCF
MCF is the IATA airport code for the military airfield serving MacDill Air Force Base in Tampa, Florida.
 E414949 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: MCF | Statement: [MacDill Air Force Base, hasIATAAirportCode, MCF]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MCF
Context triple: [MacDill Air Force Base, hasIATAAirportCode, MCF]
  • A. MCD
    MCD is a system of urban and suburban commuter rail lines in Moscow designed to function like an express metro, connecting the city with its surrounding regions.
  • B. MfS
    MfS was the official state security and intelligence service of the former East Germany, widely known for its extensive surveillance and repression of the population.
  • C. Mc
    Mc is a Gaelic patronymic prefix meaning "son of," commonly found in Scottish and Irish surnames.
  • D. MEF
    MEF is Italy’s Ministry of Economy and Finance, the government department responsible for national economic policy, public finances, and the state budget.
  • E. MRF
    MRF (Media Resource Function) is a core network component in IP Multimedia Subsystem (IMS) architectures responsible for handling media processing tasks such as mixing, transcoding, and media stream manipulation for real-time communication services.
  • 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: MCF
Triple: [MacDill Air Force Base, hasIATAAirportCode, MCF]
Generated description
MCF is the IATA airport code for the military airfield serving MacDill Air Force Base in Tampa, Florida.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MCF
Target entity description: MCF is the IATA airport code for the military airfield serving MacDill Air Force Base in Tampa, Florida.
  • A. MCD
    MCD is a system of urban and suburban commuter rail lines in Moscow designed to function like an express metro, connecting the city with its surrounding regions.
  • B. MfS
    MfS was the official state security and intelligence service of the former East Germany, widely known for its extensive surveillance and repression of the population.
  • C. Mc
    Mc is a Gaelic patronymic prefix meaning "son of," commonly found in Scottish and Irish surnames.
  • D. MEF
    MEF is Italy’s Ministry of Economy and Finance, the government department responsible for national economic policy, public finances, and the state budget.
  • E. MRF
    MRF (Media Resource Function) is a core network component in IP Multimedia Subsystem (IMS) architectures responsible for handling media processing tasks such as mixing, transcoding, and media stream manipulation for real-time communication services.
  • 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_69aed9685f70819086932777aec8d959 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69af0219f0e48190b0a925f09d858d65 completed March 9, 2026, 5:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69b576b96e588190bdf346a66a95138a completed March 14, 2026, 2:54 p.m.
NEDg Description generation batch_69b577d391ac8190b6062b1f64e2e7e8 completed March 14, 2026, 2:59 p.m.
NED2 Entity disambiguation (via description) batch_69b5787ed214819092fc425152069df9 completed March 14, 2026, 3:02 p.m.
Created at: March 9, 2026, 3:41 p.m.