Triple

T4739494
Position Surface form Disambiguated ID Type / Status
Subject Jackson–Medgar Wiley Evers International Airport E105203 entity
Predicate IATAcode P418 FINISHED
Object JAN
JAN is the three-letter IATA airport code for Jackson–Medgar Wiley Evers International Airport serving Jackson, Mississippi.
 E467122 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: JAN | Statement: [Jackson–Medgar Wiley Evers International Airport, IATAcode, JAN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: JAN
Context triple: [Jackson–Medgar Wiley Evers International Airport, IATAcode, JAN]
  • A. JANU
    JANU is the Japan Association of National Universities, a representative body that coordinates and advocates for Japan’s national universities.
  • B. Jan
    Jan is the given name of the Dutch mathematician and philosopher Luitzen Egbertus Jan Brouwer, a founder of intuitionism in the foundations of mathematics.
  • C. Jan
    Jan is an alternative romanization of the name Zhan, used to represent the same underlying name in different transliteration systems.
  • D. Jan
    Jan is a fictional character appearing in the Traveling Wilburys’ song “Tweeter and the Monkey Man,” which tells a noir-style crime story.
  • E. Jan
    Jan is a common Dutch given name, often used as a masculine form of "John" and borne by many notable figures in the Netherlands and other Dutch-speaking regions.
  • 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: JAN
Triple: [Jackson–Medgar Wiley Evers International Airport, IATAcode, JAN]
Generated description
JAN is the three-letter IATA airport code for Jackson–Medgar Wiley Evers International Airport serving Jackson, Mississippi.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: JAN
Target entity description: JAN is the three-letter IATA airport code for Jackson–Medgar Wiley Evers International Airport serving Jackson, Mississippi.
  • A. JANU
    JANU is the Japan Association of National Universities, a representative body that coordinates and advocates for Japan’s national universities.
  • B. Jan
    Jan is the given name of the Dutch mathematician and philosopher Luitzen Egbertus Jan Brouwer, a founder of intuitionism in the foundations of mathematics.
  • C. Jan
    Jan is an alternative romanization of the name Zhan, used to represent the same underlying name in different transliteration systems.
  • D. Jan
    Jan is a fictional character appearing in the Traveling Wilburys’ song “Tweeter and the Monkey Man,” which tells a noir-style crime story.
  • E. Jan
    Jan is a common Dutch given name, often used as a masculine form of "John" and borne by many notable figures in the Netherlands and other Dutch-speaking regions.
  • 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_69bd43ef87a48190a5bc3600711aa032 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6486f8608190908e43b777810c44 completed March 20, 2026, 3:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69be3a1796608190972865b2f6beef05 completed March 21, 2026, 6:26 a.m.
NEDg Description generation batch_69be3d2063e48190afb3fdfd5ad6749f completed March 21, 2026, 6:39 a.m.
NED2 Entity disambiguation (via description) batch_69be3d99a288819088e42e04de5c17a4 completed March 21, 2026, 6:41 a.m.
Created at: March 20, 2026, 1:19 p.m.