Triple

T7283139
Position Surface form Disambiguated ID Type / Status
Subject Congo Airways E163798 entity
Predicate cityServed P82 FINISHED
Object Kindu
Kindu is a city in the eastern Democratic Republic of the Congo that serves as the capital of Maniema Province and an important regional transport hub.
 E654235 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: Kindu | Statement: [Congo Airways, cityServed, Kindu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kindu
Context triple: [Congo Airways, cityServed, Kindu]
  • A. Kandia
    Kandia is a remote valley and settlement area located within Pakistan’s Kohistan mountain ranges, known for its rugged terrain and isolated communities.
  • B. Kibondo
    Kibondo is a town in western Tanzania that serves as an administrative and commercial center in the Kigoma Region.
  • C. Datooga
    Datooga is a Southern Nilotic language spoken primarily by the Datooga people of north-central Tanzania.
  • D. Kabaena
    Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly landscapes.
  • E. Buhera
    Buhera is a rural town and district center in eastern Zimbabwe known for its agricultural activities and location within Manicaland Province.
  • 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: Kindu
Triple: [Congo Airways, cityServed, Kindu]
Generated description
Kindu is a city in the eastern Democratic Republic of the Congo that serves as the capital of Maniema Province and an important regional transport hub.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kindu
Target entity description: Kindu is a city in the eastern Democratic Republic of the Congo that serves as the capital of Maniema Province and an important regional transport hub.
  • A. Kandia
    Kandia is a remote valley and settlement area located within Pakistan’s Kohistan mountain ranges, known for its rugged terrain and isolated communities.
  • B. Kibondo
    Kibondo is a town in western Tanzania that serves as an administrative and commercial center in the Kigoma Region.
  • C. Datooga
    Datooga is a Southern Nilotic language spoken primarily by the Datooga people of north-central Tanzania.
  • D. Kabaena
    Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly landscapes.
  • E. Buhera
    Buhera is a rural town and district center in eastern Zimbabwe known for its agricultural activities and location within Manicaland Province.
  • 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_69c6886093b88190a254b1ce6db8bae7 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6eb4ec2088190a6713eaa221d49a6 completed March 27, 2026, 8:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7db3ae6a08190820c7096cbfea521 completed March 28, 2026, 1:44 p.m.
NEDg Description generation batch_69c7dbe3e2ac8190a112ff01244f6a81 completed March 28, 2026, 1:47 p.m.
NED2 Entity disambiguation (via description) batch_69c7dfc15d2c8190afcf8572ff3dbb6d completed March 28, 2026, 2:03 p.m.
Created at: March 27, 2026, 2:59 p.m.