Triple

T9099742
Position Surface form Disambiguated ID Type / Status
Subject Orang Asli E218121 entity
Predicate abbreviation P43 FINISHED
Object JAKOA
JAKOA is the Malaysian government agency responsible for the welfare, development, and affairs of the Indigenous Orang Asli communities.
 E778141 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: JAKOA | Statement: [Orang Asli, abbreviation, JAKOA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: JAKOA
Context triple: [Orang Asli, abbreviation, JAKOA]
  • A. Jaku
    Jaku is a lesser-known Bantu language belonging to the Jarawan subgroup, spoken by a small community in West Africa.
  • B. Jakan
    Jakan is an alternative name for the Yakan, an indigenous ethnolinguistic group primarily inhabiting Basilan Island in the southern Philippines.
  • C. Jok
    Jok is an alternative spelling of "Jock," a term commonly used as a nickname or to describe an athletic or sports-oriented person.
  • D. Jak
    Jak is the main protagonist of the Jak and Daxter video game series, a heroic adventurer who battles oppressive regimes and dark forces across multiple worlds.
  • E. Jimo
    Jimo is a county-level city under the administration of Qingdao in eastern China's Shandong Province, known for its historical heritage and rapidly developing economy.
  • 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: JAKOA
Triple: [Orang Asli, abbreviation, JAKOA]
Generated description
JAKOA is the Malaysian government agency responsible for the welfare, development, and affairs of the Indigenous Orang Asli communities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: JAKOA
Target entity description: JAKOA is the Malaysian government agency responsible for the welfare, development, and affairs of the Indigenous Orang Asli communities.
  • A. Jaku
    Jaku is a lesser-known Bantu language belonging to the Jarawan subgroup, spoken by a small community in West Africa.
  • B. Jakan
    Jakan is an alternative name for the Yakan, an indigenous ethnolinguistic group primarily inhabiting Basilan Island in the southern Philippines.
  • C. Jok
    Jok is an alternative spelling of "Jock," a term commonly used as a nickname or to describe an athletic or sports-oriented person.
  • D. Jak
    Jak is the main protagonist of the Jak and Daxter video game series, a heroic adventurer who battles oppressive regimes and dark forces across multiple worlds.
  • E. Jimo
    Jimo is a county-level city under the administration of Qingdao in eastern China's Shandong Province, known for its historical heritage and rapidly developing economy.
  • 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_69ca83d9844081908e561e367fda6d45 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc9710ac04819096b9c8d3399b9c35 completed April 1, 2026, 3:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69d01824ee2081909cc5e6ae33fab2e5 completed April 3, 2026, 7:42 p.m.
NEDg Description generation batch_69d019666cb08190b66298ff86a7e1af completed April 3, 2026, 7:47 p.m.
NED2 Entity disambiguation (via description) batch_69d01a700ce48190868d445bde2462dc completed April 3, 2026, 7:52 p.m.
Created at: March 30, 2026, 7:15 p.m.