Triple

T16794632
Position Surface form Disambiguated ID Type / Status
Subject Northern Region of Ghana E408199 entity
Predicate hasAirport P105 FINISHED
Object Tamale Airport
Tamale Airport is a regional airport in northern Ghana that serves the city of Tamale and acts as a key air transport hub for the area.
E1235141 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: Tamale Airport | Statement: [Northern Region of Ghana, hasAirport, Tamale Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tamale Airport
Context triple: [Northern Region of Ghana, hasAirport, Tamale Airport]
  • A. Sauce Viejo Airport
    Sauce Viejo Airport is a regional airport serving the city of Santa Fe and its surrounding area in Argentina.
  • B. El Caraño Airport
    El Caraño Airport is the main public airport serving the city of Quibdó in Colombia’s Chocó Department.
  • C. Guerrero Negro Airport
    Guerrero Negro Airport is a small regional airport in Baja California Sur, Mexico, serving the town of Guerrero Negro and its surrounding area.
  • D. Vilo Acuña Airport
    Vilo Acuña Airport is the main airport serving the resort island of Cayo Largo del Sur in Cuba, handling domestic and international tourist flights.
  • E. Maya-Maya Airport
    Maya-Maya Airport is the main international airport serving Brazzaville, the capital city of the Republic of the Congo.
  • 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: Tamale Airport
Triple: [Northern Region of Ghana, hasAirport, Tamale Airport]
Generated description
Tamale Airport is a regional airport in northern Ghana that serves the city of Tamale and acts as a key air transport hub for the area.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tamale Airport
Target entity description: Tamale Airport is a regional airport in northern Ghana that serves the city of Tamale and acts as a key air transport hub for the area.
  • A. Sauce Viejo Airport
    Sauce Viejo Airport is a regional airport serving the city of Santa Fe and its surrounding area in Argentina.
  • B. El Caraño Airport
    El Caraño Airport is the main public airport serving the city of Quibdó in Colombia’s Chocó Department.
  • C. Guerrero Negro Airport
    Guerrero Negro Airport is a small regional airport in Baja California Sur, Mexico, serving the town of Guerrero Negro and its surrounding area.
  • D. Vilo Acuña Airport
    Vilo Acuña Airport is the main airport serving the resort island of Cayo Largo del Sur in Cuba, handling domestic and international tourist flights.
  • E. Maya-Maya Airport
    Maya-Maya Airport is the main international airport serving Brazzaville, the capital city of the Republic of the Congo.
  • 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_69d88393905081908d00a86b99996ac8 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b2a8b66c8190b83d8af85d2b23a8 completed April 18, 2026, 4:34 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00b28b77188190b8d87fca1b5dde5d completed May 10, 2026, 4:30 p.m.
NEDg Description generation batch_6a00b32d2a588190b59bad56f8817bce completed May 10, 2026, 4:32 p.m.
NED2 Entity disambiguation (via description) batch_6a00b3d14b3c819081f435777f47eca3 completed May 10, 2026, 4:35 p.m.
Created at: April 10, 2026, 5:22 a.m.