Triple

T12556314
Position Surface form Disambiguated ID Type / Status
Subject Gcaleka E295225 entity
Predicate associatedWith P37 FINISHED
Object Gcaleka sub-group
The Gcaleka sub-group is a major lineage of the Xhosa people in South Africa, historically known for its royal leadership and cultural influence in the Eastern Cape region.
 E990806 NE FINISHED

Named-entity recognition

Before disambiguation, gpt-5-mini classified whether the object phrase is a named entity — the step behind the object's NE type shown above.

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: Gcaleka sub-group | Statement: [Gcaleka, associatedWith, Gcaleka sub-group]

Disambiguation candidates (2 decisions)

The exact options the model was shown at each disambiguation step, with the option it chose highlighted — the evidence behind this triple's disambiguated ids.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gcaleka sub-group
Context triple: [Gcaleka, associatedWith, Gcaleka sub-group]
  • A. Tswa-Ronga group
    The Tswa-Ronga group is a closely related cluster of Bantu languages spoken primarily in southern Mozambique and neighboring regions, encompassing varieties such as Tswa, Ronga, and Tsonga.
  • B. Laiyolo–Kaili subgroup
    The Laiyolo–Kaili subgroup is a branch of the Austronesian language family comprising closely related languages spoken primarily in Sulawesi, Indonesia.
  • C. Nalik–Notsi subgroup
    The Nalik–Notsi subgroup is a branch of the Western Bismarck languages comprising closely related Oceanic languages spoken primarily in New Ireland, Papua New Guinea.
  • D. Dorla subgroup
    The Dorla subgroup is a distinct community within the broader Gondi people, characterized by its own cultural practices, dialectal features, and regional identity in central India.
  • E. Moingwena tribe
    The Moingwena tribe was a Native American group historically associated with the Illinois Confederation in the central Mississippi River valley region.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gcaleka sub-group
Target entity description: The Gcaleka sub-group is a major lineage of the Xhosa people in South Africa, historically known for its royal leadership and cultural influence in the Eastern Cape region.
  • A. Tswa-Ronga group
    The Tswa-Ronga group is a closely related cluster of Bantu languages spoken primarily in southern Mozambique and neighboring regions, encompassing varieties such as Tswa, Ronga, and Tsonga.
  • B. Laiyolo–Kaili subgroup
    The Laiyolo–Kaili subgroup is a branch of the Austronesian language family comprising closely related languages spoken primarily in Sulawesi, Indonesia.
  • C. Nalik–Notsi subgroup
    The Nalik–Notsi subgroup is a branch of the Western Bismarck languages comprising closely related Oceanic languages spoken primarily in New Ireland, Papua New Guinea.
  • D. Dorla subgroup
    The Dorla subgroup is a distinct community within the broader Gondi people, characterized by its own cultural practices, dialectal features, and regional identity in central India.
  • E. Moingwena tribe
    The Moingwena tribe was a Native American group historically associated with the Illinois Confederation in the central Mississippi River valley region.
  • F. None of above. chosen

How the object was described

The object's one-sentence description was generated by prompting gpt-5.1 with the object name and this triple as context.

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: Gcaleka sub-group
Triple: [Gcaleka, associatedWith, Gcaleka sub-group]
Generated description
The Gcaleka sub-group is a major lineage of the Xhosa people in South Africa, historically known for its royal leadership and cultural influence in the Eastern Cape region.

Provenance (5 batches)

Stage Batch ID Job type Status
creating batch_69d6ad9cac2c81908e8a7bed82d1e21d elicitation completed
NER batch_69d95490d2708190857f0cb9b8dd6a30 ner completed
NED1 batch_69f655895c9c819082f41e79906567c6 ned_source_triple completed
NED2 batch_69f65a414118819095049600f1ad6d63 ned_description completed
NEDg batch_69f6599e89708190bc1d38e9702d7626 nedg completed
Created at: April 8, 2026, 11:47 p.m.