Triple

T16259994
Position Surface form Disambiguated ID Type / Status
Subject Tsumeb E394727 entity
Predicate hasAirport P105 FINISHED
Object Tsumeb Airport
Tsumeb Airport is a small public airport serving the town of Tsumeb in northern Namibia, primarily handling regional and domestic flights.
E1234369 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: Tsumeb Airport | Statement: [Tsumeb, hasAirport, Tsumeb Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tsumeb Airport
Context triple: [Tsumeb, hasAirport, Tsumeb Airport]
  • A. Makung Airport
    Makung Airport is a regional airport serving the Penghu Islands in Taiwan, providing domestic flights that connect the archipelago with major cities on the Taiwanese mainland.
  • B. Kirakira Airport
    Kirakira Airport is a small regional airfield serving the town of Kirakira and surrounding communities in Makira-Ulawa Province of the Solomon Islands.
  • C. Osubi Airport
    Osubi Airport is a domestic airport serving the city of Warri and its surrounding region in Delta State, Nigeria.
  • D. Nakashibetsu Airport
    Nakashibetsu Airport is a regional airport in eastern Hokkaido, Japan, serving as an air gateway to the Nemuro and Shiretoko areas.
  • E. Sado Airport
    Sado Airport is a regional airport serving Sado Island in Niigata Prefecture, Japan, providing domestic air connections to the mainland.
  • 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: Tsumeb Airport
Triple: [Tsumeb, hasAirport, Tsumeb Airport]
Generated description
Tsumeb Airport is a small public airport serving the town of Tsumeb in northern Namibia, primarily handling regional and domestic flights.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tsumeb Airport
Target entity description: Tsumeb Airport is a small public airport serving the town of Tsumeb in northern Namibia, primarily handling regional and domestic flights.
  • A. Makung Airport
    Makung Airport is a regional airport serving the Penghu Islands in Taiwan, providing domestic flights that connect the archipelago with major cities on the Taiwanese mainland.
  • B. Kirakira Airport
    Kirakira Airport is a small regional airfield serving the town of Kirakira and surrounding communities in Makira-Ulawa Province of the Solomon Islands.
  • C. Osubi Airport
    Osubi Airport is a domestic airport serving the city of Warri and its surrounding region in Delta State, Nigeria.
  • D. Nakashibetsu Airport
    Nakashibetsu Airport is a regional airport in eastern Hokkaido, Japan, serving as an air gateway to the Nemuro and Shiretoko areas.
  • E. Sado Airport
    Sado Airport is a regional airport serving Sado Island in Niigata Prefecture, Japan, providing domestic air connections to the mainland.
  • 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_69d87f221d8081909b0b2063e7528ba2 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e245c3082c8190a1c9f92b255fdbb6 completed April 17, 2026, 2:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00b276be5c8190a42ce541168ab7d0 completed May 10, 2026, 4:29 p.m.
NEDg Description generation batch_6a00b33f21a48190b3178aa1241bb85a completed May 10, 2026, 4:33 p.m.
NED2 Entity disambiguation (via description) batch_6a00b3afb3708190ab7d78561a2e778c completed May 10, 2026, 4:34 p.m.
Created at: April 10, 2026, 5:04 a.m.