Triple

T21073573
Position Surface form Disambiguated ID Type / Status
Subject Haut-Uélé Province E519171 entity
Predicate containsTown P847 FINISHED
Object Dungu
Dungu is a town in northeastern Democratic Republic of the Congo, known as a local administrative and trading center near the Garamba National Park.
 E1467121 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: Dungu | Statement: [Haut-Uélé Province, containsTown, Dungu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dungu
Context triple: [Haut-Uélé Province, containsTown, Dungu]
  • A. Ndungu
    Ndungu is a settlement located within Kenya’s Same District, known primarily as a small local community in this administrative area.
  • B. Ndugu
    Ndugu is a surname of likely African origin borne by various individuals, including those with the given name Bailey.
  • C. Dzundza
    Dzundza is the surname of George Dzundza, a German-American actor known for roles in films like "Crimson Tide" and the early seasons of "Law & Order."
  • D. Noukadubi
    Noukadubi is a 2011 Bengali-language film adaptation of Rabindranath Tagore’s novel of the same name, directed by Rituparno Ghosh.
  • E. Marapu
    Marapu is the indigenous ancestral belief system of the Sumbanese people, characterized by animism, ancestor worship, and elaborate ritual practices.
  • 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: Dungu
Triple: [Haut-Uélé Province, containsTown, Dungu]
Generated description
Dungu is a town in northeastern Democratic Republic of the Congo, known as a local administrative and trading center near the Garamba National Park.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dungu
Target entity description: Dungu is a town in northeastern Democratic Republic of the Congo, known as a local administrative and trading center near the Garamba National Park.
  • A. Ndungu
    Ndungu is a settlement located within Kenya’s Same District, known primarily as a small local community in this administrative area.
  • B. Ndugu
    Ndugu is a surname of likely African origin borne by various individuals, including those with the given name Bailey.
  • C. Dzundza
    Dzundza is the surname of George Dzundza, a German-American actor known for roles in films like "Crimson Tide" and the early seasons of "Law & Order."
  • D. Noukadubi
    Noukadubi is a 2011 Bengali-language film adaptation of Rabindranath Tagore’s novel of the same name, directed by Rituparno Ghosh.
  • E. Marapu
    Marapu is the indigenous ancestral belief system of the Sumbanese people, characterized by animism, ancestor worship, and elaborate ritual practices.
  • 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_69e0b506e59c8190849b71ed07929215 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e702d491a08190a9f5f28c0b72d38c completed April 21, 2026, 4:53 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0965d73eb481908cd4a9469ab7a5a1 completed May 17, 2026, 6:53 a.m.
NEDg Description generation batch_6a096630a5e881909b696a499c942ae5 completed May 17, 2026, 6:54 a.m.
NED2 Entity disambiguation (via description) batch_6a09668b8c7c81908c1ec2392d18434a completed May 17, 2026, 6:56 a.m.
Created at: April 16, 2026, 2:47 p.m.