Triple

T34712672
Position Surface form Disambiguated ID Type / Status
Subject Pondoland E1000687 entity
Predicate historicPeople P34335 FINISHED
Object Faku kaNgqungqushe
Faku kaNgqungqushe was a prominent 19th-century king of Pondoland who played a key role in unifying the Mpondo people and navigating early colonial pressures in southeastern Africa.
 E2109430 NE FINISHED

How this triple was built (3 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: Faku kaNgqungqushe | Statement: [Pondoland, historicPeople, Faku kaNgqungqushe]
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: Faku kaNgqungqushe
Triple: [Pondoland, historicPeople, Faku kaNgqungqushe]
Generated description
Faku kaNgqungqushe was a prominent 19th-century king of Pondoland who played a key role in unifying the Mpondo people and navigating early colonial pressures in southeastern Africa.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: historicPeople
Context triple: [Pondoland, historicPeople, Faku kaNgqungqushe]
  • A. historicalPeople chosen
    Indicates that the related entities are people who lived in or are associated with a past historical period or context.
  • B. historicalPeopleCenter
    Indicates a relationship where a center, institution, or focal point is dedicated to, focused on, or primarily concerned with historical people.
  • C. historicalFigure
    Indicates that an entity is recognized as a notable person from the past who played a significant role in history.
  • D. roleInHumanHistory
    Indicates the function, influence, or significance that an entity has had within the course of human history.
  • E. historicResident
    Indicates that an entity lived or resided in a place during a historically significant period or in the past.
  • F. None of above.

Provenance (6 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_69f76dad3f108190a280fd0a2f4ee89a completed May 3, 2026, 3:45 p.m.
NER Named-entity recognition batch_6a007dd341108190a1d03eab46041694 completed May 10, 2026, 12:45 p.m.
NED1 Entity disambiguation (via context triple) batch_6a375bdec280819085d61ce67673489f completed June 21, 2026, 3:34 a.m.
NEDg Description generation batch_6a375ce7a72c819098f1ff70b5e9dc2f completed June 21, 2026, 3:39 a.m.
NED2 Entity disambiguation (via description) batch_6a375d775e748190847a041f568b50d8 completed June 21, 2026, 3:41 a.m.
PD Predicate disambiguation batch_6a007b1fe2a881909ec50a1e65e4651b completed May 10, 2026, 12:33 p.m.
Created at: May 3, 2026, 3:59 p.m.