Triple

T10103344
Position Surface form Disambiguated ID Type / Status
Subject Orang Seletar E216255 entity
Predicate relatedGroup P37 FINISHED
Object Jakun people
The Jakun people are an indigenous Orang Asli group of Peninsular Malaysia, traditionally forest-dwelling and engaged in hunting, gathering, and small-scale agriculture, with their own distinct language and cultural practices.
E930256 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: Jakun people | Statement: [Orang Seletar, relatedGroup, Jakun people]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jakun people
Context triple: [Orang Seletar, relatedGroup, Jakun people]
  • A. Paakantji people
    The Paakantji people are an Aboriginal Australian group traditionally associated with the Darling River region of western New South Wales, known for their rich cultural heritage, language, and enduring connection to their ancestral lands.
  • B. Kankuamo people
    The Kankuamo people are an Indigenous group of the Sierra Nevada de Santa Marta in northern Colombia, closely related culturally and linguistically to other Arhuaco-speaking communities of the region.
  • C. Kitanemuk people
    The Kitanemuk people are an Indigenous Native American group traditionally inhabiting the Tehachapi Mountains and adjacent regions of Southern California, known for their distinct Takic language and cultural practices.
  • D. Teko people
    The Teko people are an Indigenous group of the Guiana Shield region, traditionally living in the rainforest of French Guiana and neighboring areas, with a distinct language and culture closely tied to the Amazonian environment.
  • E. Tadaksahak people
    The Tadaksahak people are a semi-nomadic ethnic group of the Sahel region, primarily in Mali, known for their pastoralist lifestyle and distinct Afro-Asiatic language and culture influenced by neighboring Tuareg communities.
  • 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: Jakun people
Triple: [Orang Seletar, relatedGroup, Jakun people]
Generated description
The Jakun people are an indigenous Orang Asli group of Peninsular Malaysia, traditionally forest-dwelling and engaged in hunting, gathering, and small-scale agriculture, with their own distinct language and cultural practices.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jakun people
Target entity description: The Jakun people are an indigenous Orang Asli group of Peninsular Malaysia, traditionally forest-dwelling and engaged in hunting, gathering, and small-scale agriculture, with their own distinct language and cultural practices.
  • A. Paakantji people
    The Paakantji people are an Aboriginal Australian group traditionally associated with the Darling River region of western New South Wales, known for their rich cultural heritage, language, and enduring connection to their ancestral lands.
  • B. Kankuamo people
    The Kankuamo people are an Indigenous group of the Sierra Nevada de Santa Marta in northern Colombia, closely related culturally and linguistically to other Arhuaco-speaking communities of the region.
  • C. Kitanemuk people
    The Kitanemuk people are an Indigenous Native American group traditionally inhabiting the Tehachapi Mountains and adjacent regions of Southern California, known for their distinct Takic language and cultural practices.
  • D. Teko people
    The Teko people are an Indigenous group of the Guiana Shield region, traditionally living in the rainforest of French Guiana and neighboring areas, with a distinct language and culture closely tied to the Amazonian environment.
  • E. Tadaksahak people
    The Tadaksahak people are a semi-nomadic ethnic group of the Sahel region, primarily in Mali, known for their pastoralist lifestyle and distinct Afro-Asiatic language and culture influenced by neighboring Tuareg communities.
  • 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_69ca83d039f08190b9d10363221c69fb completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cdd09af07c819099774af46ebf62d7 completed April 2, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69e623a9711081908eac4238a717305c completed April 20, 2026, 1:01 p.m.
NEDg Description generation batch_69e62aee8fb88190b5973c61e692087f completed April 20, 2026, 1:32 p.m.
NED2 Entity disambiguation (via description) batch_69e67394e7f081908fcc602c84eb4a65 completed April 20, 2026, 6:42 p.m.
Created at: March 30, 2026, 9:03 p.m.