Triple

T7879001
Position Surface form Disambiguated ID Type / Status
Subject Kotoka International Airport E182929 entity
Predicate hubFor P423 FINISHED
Object Passion Air
Passion Air is a Ghanaian domestic airline based in Accra that operates passenger flights connecting major cities within Ghana.
 E701123 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: Passion Air | Statement: [Kotoka International Airport, hubFor, Passion Air]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Passion Air
Context triple: [Kotoka International Airport, hubFor, Passion Air]
  • A. Sky Express
    Sky Express is a Greek regional airline that operates domestic flights connecting numerous islands and mainland cities within Greece.
  • B. Blue Air
    Blue Air is a Romanian low-cost airline that operated scheduled passenger flights across Europe.
  • C. Edelweiss Air
    Edelweiss Air is a Swiss leisure airline based in Zurich that operates holiday and charter flights to vacation destinations worldwide.
  • D. Air Nostrum
    Air Nostrum is a Spanish regional airline that operates flights under the Iberia Regional brand, connecting smaller cities with Iberia’s main network.
  • E. Boutique Air
    Boutique Air is a small U.S. regional airline that operates scheduled commuter flights using turboprop aircraft, often serving smaller communities and offering connections to major hubs.
  • 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: Passion Air
Triple: [Kotoka International Airport, hubFor, Passion Air]
Generated description
Passion Air is a Ghanaian domestic airline based in Accra that operates passenger flights connecting major cities within Ghana.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Passion Air
Target entity description: Passion Air is a Ghanaian domestic airline based in Accra that operates passenger flights connecting major cities within Ghana.
  • A. Sky Express
    Sky Express is a Greek regional airline that operates domestic flights connecting numerous islands and mainland cities within Greece.
  • B. Blue Air
    Blue Air is a Romanian low-cost airline that operated scheduled passenger flights across Europe.
  • C. Edelweiss Air
    Edelweiss Air is a Swiss leisure airline based in Zurich that operates holiday and charter flights to vacation destinations worldwide.
  • D. Air Nostrum
    Air Nostrum is a Spanish regional airline that operates flights under the Iberia Regional brand, connecting smaller cities with Iberia’s main network.
  • E. Boutique Air
    Boutique Air is a small U.S. regional airline that operates scheduled commuter flights using turboprop aircraft, often serving smaller communities and offering connections to major hubs.
  • 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_69ca828a17248190b46defe758bc5ad3 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb39be7ab88190affcd353a0cd37fa completed March 31, 2026, 3:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5b86c20081909aa029cda7c48d44 completed March 31, 2026, 5:28 a.m.
NEDg Description generation batch_69cb7631d10881908e3c7dacb98520cd completed March 31, 2026, 7:22 a.m.
NED2 Entity disambiguation (via description) batch_69cbbf847f3c819092d690d8d65f6d60 completed March 31, 2026, 12:35 p.m.
Created at: March 30, 2026, 4:57 p.m.