Triple

T10956891
Position Surface form Disambiguated ID Type / Status
Subject Arusha Airport E258868 entity
Predicate IATAcode P418 FINISHED
Object ARK
ARK is the IATA airport code for Arusha Airport, a regional airport serving the city of Arusha in northern Tanzania near major safari destinations.
 E896644 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: ARK | Statement: [Arusha Airport, IATAcode, ARK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ARK
Context triple: [Arusha Airport, IATAcode, ARK]
  • A. ARK
    ARK is the standard abbreviation used for the Arkansas Travelers Minor League Baseball team.
  • B. Ark
    Ark is a hard science fiction novel by Stephen Baxter that explores humanity's desperate attempts to escape a flooded Earth via interstellar ark ships.
  • C. Ark
    Ark was one of the two ships that carried the first group of English settlers to establish the Maryland colony in North America in the 17th century.
  • D. Ark
    Ark is the massive, generation-starship habitat that serves as the primary setting of the 1970s science fiction television series "The Starlost."
  • E. Ark
    Ark is a graphical file archiver and compression utility for the KDE desktop environment that allows users to create, view, and extract archives in various formats.
  • 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: ARK
Triple: [Arusha Airport, IATAcode, ARK]
Generated description
ARK is the IATA airport code for Arusha Airport, a regional airport serving the city of Arusha in northern Tanzania near major safari destinations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ARK
Target entity description: ARK is the IATA airport code for Arusha Airport, a regional airport serving the city of Arusha in northern Tanzania near major safari destinations.
  • A. ARK
    ARK is the standard abbreviation used for the Arkansas Travelers Minor League Baseball team.
  • B. Ark
    Ark is a hard science fiction novel by Stephen Baxter that explores humanity's desperate attempts to escape a flooded Earth via interstellar ark ships.
  • C. Ark
    Ark was one of the two ships that carried the first group of English settlers to establish the Maryland colony in North America in the 17th century.
  • D. Ark
    Ark is the massive, generation-starship habitat that serves as the primary setting of the 1970s science fiction television series "The Starlost."
  • E. Ark
    Ark is a graphical file archiver and compression utility for the KDE desktop environment that allows users to create, view, and extract archives in various formats.
  • 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_69d6aa88500c819097d7032ca578e74f completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d771260e9881909401a7a7466e1b8a completed April 9, 2026, 9:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2d7439204819092fcd061a161fd7b completed April 18, 2026, 12:58 a.m.
NEDg Description generation batch_69e2ff1ddd2c8190b31f5007f7492a4e completed April 18, 2026, 3:48 a.m.
NED2 Entity disambiguation (via description) batch_69e3260494bc81909e3dd4829697fb72 completed April 18, 2026, 6:34 a.m.
Created at: April 8, 2026, 9:23 p.m.