Triple

T7019413
Position Surface form Disambiguated ID Type / Status
Subject Precision Air E162779 entity
Predicate cityServed P82 FINISHED
Object Mtwara
Mtwara is a coastal city in southern Tanzania that serves as a regional economic and transport hub, including an airport served by domestic airlines.
 E638003 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: Mtwara | Statement: [Precision Air, cityServed, Mtwara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mtwara
Context triple: [Precision Air, cityServed, Mtwara]
  • A. Mbeya
    Mbeya is a major city in southwestern Tanzania, serving as a commercial and transport hub near the Zambian border.
  • B. Butare
    Butare is a city in southern Rwanda that became a significant site of massacres and atrocities during the 1994 Rwandan genocide.
  • C. Bidassoa
    Bidassoa is a river in the western Pyrenees that forms part of the border between France and Spain before flowing into the Bay of Biscay.
  • D. Bukavu
    Bukavu is a major city in the eastern Democratic Republic of the Congo, located on the southwestern shore of Lake Kivu near the Rwandan border.
  • E. Gitega
    Gitega is the political and administrative capital city of Burundi, located in the central part of the country.
  • 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: Mtwara
Triple: [Precision Air, cityServed, Mtwara]
Generated description
Mtwara is a coastal city in southern Tanzania that serves as a regional economic and transport hub, including an airport served by domestic airlines.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mtwara
Target entity description: Mtwara is a coastal city in southern Tanzania that serves as a regional economic and transport hub, including an airport served by domestic airlines.
  • A. Mbeya
    Mbeya is a major city in southwestern Tanzania, serving as a commercial and transport hub near the Zambian border.
  • B. Butare
    Butare is a city in southern Rwanda that became a significant site of massacres and atrocities during the 1994 Rwandan genocide.
  • C. Bidassoa
    Bidassoa is a river in the western Pyrenees that forms part of the border between France and Spain before flowing into the Bay of Biscay.
  • D. Bukavu
    Bukavu is a major city in the eastern Democratic Republic of the Congo, located on the southwestern shore of Lake Kivu near the Rwandan border.
  • E. Gitega
    Gitega is the political and administrative capital city of Burundi, located in the central part of the country.
  • 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_69c6885b26248190a857541e3d10e299 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e1e8e36c81908c95a8181781cda4 completed March 27, 2026, 8 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7885104e881909be62c2eb12e0bcf completed March 28, 2026, 7:50 a.m.
NEDg Description generation batch_69c7891785288190974db0bca4b8f265 completed March 28, 2026, 7:53 a.m.
NED2 Entity disambiguation (via description) batch_69c78982bc308190aeffc3f786a82327 completed March 28, 2026, 7:55 a.m.
Created at: March 27, 2026, 2:34 p.m.