Triple

T1120837
Position Surface form Disambiguated ID Type / Status
Subject Zulu Kingdom E24606 entity
Predicate capital P234 FINISHED
Object Nodwengu
Nodwengu was a principal royal residence and political center of the Zulu Kingdom during the 19th century.
 E129212 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: Nodwengu | Statement: [Zulu Kingdom, capital, Nodwengu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Nodwengu
Context triple: [Zulu Kingdom, capital, Nodwengu]
  • A. Umbundu
    Umbundu is a major Bantu language spoken primarily in central and southern Angola, especially by the Ovimbundu people.
  • B. Sakubva
    Sakubva is a high-density residential suburb of Mutare in eastern Zimbabwe, known as one of the city’s oldest and most populous townships.
  • C. Mwanza
    Mwanza is a major port city in northwestern Tanzania, situated on the southern shores of Lake Victoria and serving as a key commercial and transport hub for the region.
  • D. Mtiuleti
    Mtiuleti is a mountainous historical region in northeastern Georgia known for its rugged landscapes and traditional highland villages.
  • E. Nganasan
    The Nganasan are an Indigenous Samoyedic people of northern Siberia, traditionally semi-nomadic reindeer hunters and fishers with a distinct Uralic language and culture.
  • 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: Nodwengu
Triple: [Zulu Kingdom, capital, Nodwengu]
Generated description
Nodwengu was a principal royal residence and political center of the Zulu Kingdom during the 19th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Nodwengu
Target entity description: Nodwengu was a principal royal residence and political center of the Zulu Kingdom during the 19th century.
  • A. Umbundu
    Umbundu is a major Bantu language spoken primarily in central and southern Angola, especially by the Ovimbundu people.
  • B. Sakubva
    Sakubva is a high-density residential suburb of Mutare in eastern Zimbabwe, known as one of the city’s oldest and most populous townships.
  • C. Mwanza
    Mwanza is a major port city in northwestern Tanzania, situated on the southern shores of Lake Victoria and serving as a key commercial and transport hub for the region.
  • D. Mtiuleti
    Mtiuleti is a mountainous historical region in northeastern Georgia known for its rugged landscapes and traditional highland villages.
  • E. Nganasan
    The Nganasan are an Indigenous Samoyedic people of northern Siberia, traditionally semi-nomadic reindeer hunters and fishers with a distinct Uralic language and culture.
  • 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_69a4940712c88190aa244f3fc6070a65 completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bbbe58588190a5ef6346e269d5f3 completed March 1, 2026, 10:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac539b6d9881909c3fe5890ae1f889 completed March 7, 2026, 4:34 p.m.
NEDg Description generation batch_69ac554aec048190821801070d1a4852 completed March 7, 2026, 4:41 p.m.
NED2 Entity disambiguation (via description) batch_69ac55afd8c88190b0f2bbafc33ad8b7 completed March 7, 2026, 4:43 p.m.
Created at: March 1, 2026, 7:43 p.m.