Triple

T4729583
Position Surface form Disambiguated ID Type / Status
Subject Puntland E104970 entity
Predicate hasAirport P105 FINISHED
Object Garowe Airport
Garowe Airport is the main civil aviation facility serving the city of Garowe, the capital of the Puntland region in northeastern Somalia.
E468784 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: Garowe Airport | Statement: [Puntland, hasAirport, Garowe Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Garowe Airport
Context triple: [Puntland, hasAirport, Garowe Airport]
  • A. Almaza Airport
    Almaza Airport is a historic airfield in Cairo that served as the city's main airport before the opening of Cairo International Airport.
  • B. Gardabya Airport
    Gardabya Airport is a Libyan airport serving the coastal city of Sirte and its surrounding region.
  • C. Kohat Airport
    Kohat Airport is a domestic airport serving the city of Kohat in Khyber Pakhtunkhwa, Pakistan.
  • D. Zhob Airport
    Zhob Airport is a domestic airport serving the city of Zhob in Balochistan, Pakistan, providing regional air connectivity.
  • E. Shah Makhdum Airport
    Shah Makhdum Airport is a regional domestic airport serving the city of Rajshahi in western Bangladesh.
  • 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: Garowe Airport
Triple: [Puntland, hasAirport, Garowe Airport]
Generated description
Garowe Airport is the main civil aviation facility serving the city of Garowe, the capital of the Puntland region in northeastern Somalia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Garowe Airport
Target entity description: Garowe Airport is the main civil aviation facility serving the city of Garowe, the capital of the Puntland region in northeastern Somalia.
  • A. Almaza Airport
    Almaza Airport is a historic airfield in Cairo that served as the city's main airport before the opening of Cairo International Airport.
  • B. Gardabya Airport
    Gardabya Airport is a Libyan airport serving the coastal city of Sirte and its surrounding region.
  • C. Kohat Airport
    Kohat Airport is a domestic airport serving the city of Kohat in Khyber Pakhtunkhwa, Pakistan.
  • D. Zhob Airport
    Zhob Airport is a domestic airport serving the city of Zhob in Balochistan, Pakistan, providing regional air connectivity.
  • E. Shah Makhdum Airport
    Shah Makhdum Airport is a regional domestic airport serving the city of Rajshahi in western Bangladesh.
  • 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_69bd43ed84648190ae0b7ee8e8d00482 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd646135c881909030c21a163cc619 completed March 20, 2026, 3:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69be43a86b288190ada883c345b00c72 completed March 21, 2026, 7:07 a.m.
NEDg Description generation batch_69be449593f0819092be9f4a86bb47aa completed March 21, 2026, 7:11 a.m.
NED2 Entity disambiguation (via description) batch_69be44f6031c81908fdca148b784aaf9 completed March 21, 2026, 7:12 a.m.
Created at: March 20, 2026, 1:19 p.m.