Triple

T9960743
Position Surface form Disambiguated ID Type / Status
Subject Gitega E195559 entity
Predicate hasTransport P1298 FINISHED
Object Gitega Airport
Gitega Airport is a small public airport serving the city of Gitega, the political capital of Burundi.
E831902 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: Gitega Airport | Statement: [Gitega, hasTransport, Gitega Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gitega Airport
Context triple: [Gitega, hasTransport, Gitega Airport]
  • A. Kamuzu International Airport
    Kamuzu International Airport is the main international airport serving Lilongwe and one of the primary gateways to Malawi.
  • B. Kigoma Airport
    Kigoma Airport is a public airport in western Tanzania that serves the town of Kigoma on the shores of Lake Tanganyika.
  • C. Kigali International Airport
    Kigali International Airport is Rwanda’s main international gateway, serving as the primary hub for air travel to and from the capital city of Kigali.
  • D. Matadi Tshimpi Airport
    Matadi Tshimpi Airport is a public airport serving the city of Matadi in the Kongo Central Province of the Democratic Republic of the Congo.
  • E. Mpanda Airport
    Mpanda Airport is a regional airport in western Tanzania that serves the town of Mpanda and the surrounding Katavi Region.
  • 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: Gitega Airport
Triple: [Gitega, hasTransport, Gitega Airport]
Generated description
Gitega Airport is a small public airport serving the city of Gitega, the political capital of Burundi.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Gitega Airport
Target entity description: Gitega Airport is a small public airport serving the city of Gitega, the political capital of Burundi.
  • A. Kamuzu International Airport
    Kamuzu International Airport is the main international airport serving Lilongwe and one of the primary gateways to Malawi.
  • B. Kigoma Airport
    Kigoma Airport is a public airport in western Tanzania that serves the town of Kigoma on the shores of Lake Tanganyika.
  • C. Kigali International Airport
    Kigali International Airport is Rwanda’s main international gateway, serving as the primary hub for air travel to and from the capital city of Kigali.
  • D. Matadi Tshimpi Airport
    Matadi Tshimpi Airport is a public airport serving the city of Matadi in the Kongo Central Province of the Democratic Republic of the Congo.
  • E. Mpanda Airport
    Mpanda Airport is a regional airport in western Tanzania that serves the town of Mpanda and the surrounding Katavi Region.
  • 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_69ca82eaaa008190a54fa1a9f954b9ad completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb6d219c48190b2084b0eb07ae125 completed April 2, 2026, 12:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69d23d904bbc8190ac0b28600ed2e709 completed April 5, 2026, 10:46 a.m.
NEDg Description generation batch_69d23fa1e3288190b755b3966178ad52 completed April 5, 2026, 10:55 a.m.
NED2 Entity disambiguation (via description) batch_69d24077720c81909a43ff56627095a1 completed April 5, 2026, 10:59 a.m.
Created at: March 30, 2026, 8:47 p.m.