Triple

T4784582
Position Surface form Disambiguated ID Type / Status
Subject North Kivu Province E106444 entity
Predicate hasCity P316 FINISHED
Object Walikale
Walikale is a town and territory in the mineral-rich, conflict-affected North Kivu region of the eastern Democratic Republic of the Congo.
 E468938 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: Walikale | Statement: [North Kivu Province, hasCity, Walikale]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Walikale
Context triple: [North Kivu Province, hasCity, Walikale]
  • A. Walili
    Walili, better known as Volubilis, is an ancient Roman and early Islamic city in present-day Morocco that served as the first capital of the Idrisid dynasty.
  • B. Wiphala
    The Wiphala is a multicolored, checkered flag representing the Indigenous peoples of the Andes and widely recognized as a symbol of Indigenous identity and plurinationalism in Bolivia.
  • C. Nalik
    Nalik is an Austronesian language spoken by a small community in New Ireland, Papua New Guinea.
  • D. Wakema
    Wakema is a town in Myanmar’s Ayeyarwady Region, known as the birthplace of former Burmese Prime Minister U Nu.
  • E. Walo
    Walo was a precolonial West African kingdom in the lower Senegal River region, known as one of the successor states to the Wolof Empire.
  • 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: Walikale
Triple: [North Kivu Province, hasCity, Walikale]
Generated description
Walikale is a town and territory in the mineral-rich, conflict-affected North Kivu region of the eastern Democratic Republic of the Congo.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Walikale
Target entity description: Walikale is a town and territory in the mineral-rich, conflict-affected North Kivu region of the eastern Democratic Republic of the Congo.
  • A. Walili
    Walili, better known as Volubilis, is an ancient Roman and early Islamic city in present-day Morocco that served as the first capital of the Idrisid dynasty.
  • B. Wiphala
    The Wiphala is a multicolored, checkered flag representing the Indigenous peoples of the Andes and widely recognized as a symbol of Indigenous identity and plurinationalism in Bolivia.
  • C. Nalik
    Nalik is an Austronesian language spoken by a small community in New Ireland, Papua New Guinea.
  • D. Wakema
    Wakema is a town in Myanmar’s Ayeyarwady Region, known as the birthplace of former Burmese Prime Minister U Nu.
  • E. Walo
    Walo was a precolonial West African kingdom in the lower Senegal River region, known as one of the successor states to the Wolof Empire.
  • 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_69bd43f4a9588190bf73e20bc27c03cc completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd65ae49ec81908f16248d22d1155f completed March 20, 2026, 3:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69be43dbdec88190817845e7930a18f6 completed March 21, 2026, 7:08 a.m.
NEDg Description generation batch_69be447c21d48190ab57c8761e733ff4 completed March 21, 2026, 7:10 a.m.
NED2 Entity disambiguation (via description) batch_69be45f5ebec8190b62c428b465d1bd9 completed March 21, 2026, 7:17 a.m.
Created at: March 20, 2026, 1:22 p.m.