Triple

T7723918
Position Surface form Disambiguated ID Type / Status
Subject Mpulungu E175081 entity
Predicate connectedTo P37 FINISHED
Object Mbala
Mbala is a town in northern Zambia near the Tanzanian border, known historically as a colonial-era administrative center and for its proximity to Lake Tanganyika.
 E684442 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: Mbala | Statement: [Mpulungu, connectedTo, Mbala]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mbala
Context triple: [Mpulungu, connectedTo, Mbala]
  • A. Mbalanhu
    Mbalanhu is a Bantu language variety spoken by a subgroup of the Ovambo people in northern Namibia and southern Angola.
  • B. Mbagala
    "Mbagala" is a popular hit song by Tanzanian Bongo Flava artist Diamond Platnumz that helped establish his early fame in East Africa.
  • C. Mabalako
    Mabalako is a health zone in North Kivu Province in the eastern Democratic Republic of the Congo, known for being heavily affected by Ebola outbreaks.
  • D. Mbanderu
    Mbanderu is a subgroup of the Herero people with its own distinct dialect and cultural traditions, primarily found in Namibia and Botswana.
  • E. Mbaitoli
    Mbaitoli is a local government area in southeastern Nigeria known for its predominantly Igbo population and its role within Imo State’s administrative and cultural landscape.
  • 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: Mbala
Triple: [Mpulungu, connectedTo, Mbala]
Generated description
Mbala is a town in northern Zambia near the Tanzanian border, known historically as a colonial-era administrative center and for its proximity to Lake Tanganyika.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mbala
Target entity description: Mbala is a town in northern Zambia near the Tanzanian border, known historically as a colonial-era administrative center and for its proximity to Lake Tanganyika.
  • A. Mbalanhu
    Mbalanhu is a Bantu language variety spoken by a subgroup of the Ovambo people in northern Namibia and southern Angola.
  • B. Mbagala
    "Mbagala" is a popular hit song by Tanzanian Bongo Flava artist Diamond Platnumz that helped establish his early fame in East Africa.
  • C. Mabalako
    Mabalako is a health zone in North Kivu Province in the eastern Democratic Republic of the Congo, known for being heavily affected by Ebola outbreaks.
  • D. Mbanderu
    Mbanderu is a subgroup of the Herero people with its own distinct dialect and cultural traditions, primarily found in Namibia and Botswana.
  • E. Mbaitoli
    Mbaitoli is a local government area in southeastern Nigeria known for its predominantly Igbo population and its role within Imo State’s administrative and cultural landscape.
  • 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_69c6995d541c81909eaa646b1a8369a9 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c702f39fa48190b7b8a09446b5cf78 completed March 27, 2026, 10:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8b51faa348190b4fa0b5a307c83db completed March 29, 2026, 5:14 a.m.
NEDg Description generation batch_69c8b74ee6d081908454b2d4774a3a7b completed March 29, 2026, 5:23 a.m.
NED2 Entity disambiguation (via description) batch_69c8b7af4c58819097360e89e7ea6062 completed March 29, 2026, 5:25 a.m.
Created at: March 27, 2026, 4:05 p.m.