Triple

T18383399
Position Surface form Disambiguated ID Type / Status
Subject Mazowe River E446513 entity
Predicate hasDam P8736 FINISHED
Object Mwenje Dam
Mwenje Dam is a reservoir built on the Mazowe River in Zimbabwe, primarily used for irrigation and local water supply.
 E1322264 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: Mwenje Dam | Statement: [Mazowe River, hasDam, Mwenje Dam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mwenje Dam
Context triple: [Mazowe River, hasDam, Mwenje Dam]
  • A. Zola Dam
    Zola Dam is a 19th-century hydraulic engineering project in Aix-en-Provence, France, designed by engineer François Zola and notable as an early example of modern dam construction.
  • B. Mankwe Dam
    Mankwe Dam is a large artificial lake and key wildlife viewing hotspot located within South Africa’s Pilanesberg National Park.
  • C. Ohangwena
    Ohangwena is a settlement in northern Namibia that lends its name to the surrounding Ohangwena Region.
  • D. Kiambere Dam
    Kiambere Dam is a major hydroelectric power facility in Kenya that harnesses the flow of the Tana River to generate electricity.
  • E. Usuma Dam
    Usuma Dam is a major water reservoir near Abuja, Nigeria, that supplies potable water to the capital and serves as a key component of the region’s water infrastructure.
  • 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: Mwenje Dam
Triple: [Mazowe River, hasDam, Mwenje Dam]
Generated description
Mwenje Dam is a reservoir built on the Mazowe River in Zimbabwe, primarily used for irrigation and local water supply.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mwenje Dam
Target entity description: Mwenje Dam is a reservoir built on the Mazowe River in Zimbabwe, primarily used for irrigation and local water supply.
  • A. Zola Dam
    Zola Dam is a 19th-century hydraulic engineering project in Aix-en-Provence, France, designed by engineer François Zola and notable as an early example of modern dam construction.
  • B. Mankwe Dam
    Mankwe Dam is a large artificial lake and key wildlife viewing hotspot located within South Africa’s Pilanesberg National Park.
  • C. Ohangwena
    Ohangwena is a settlement in northern Namibia that lends its name to the surrounding Ohangwena Region.
  • D. Kiambere Dam
    Kiambere Dam is a major hydroelectric power facility in Kenya that harnesses the flow of the Tana River to generate electricity.
  • E. Usuma Dam
    Usuma Dam is a major water reservoir near Abuja, Nigeria, that supplies potable water to the capital and serves as a key component of the region’s water infrastructure.
  • 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_69d8b9f370b88190b1e5081c2c238e7f completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e5179c931c8190b1c7c8284f42f7b7 completed April 19, 2026, 5:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03e23cf864819085d0fcf6b10c066c completed May 13, 2026, 2:30 a.m.
NEDg Description generation batch_6a03e33280a08190b63cdb99ab5741b5 completed May 13, 2026, 2:34 a.m.
NED2 Entity disambiguation (via description) batch_6a03e3ac2f4081908e086f8efd1393ae completed May 13, 2026, 2:36 a.m.
Created at: April 10, 2026, 10:45 a.m.