Triple

T22296623
Position Surface form Disambiguated ID Type / Status
Subject Jarawan languages E551137 entity
Predicate hasMember P10 FINISHED
Object Jaku language
The Jaku language is a lesser-known Jarawan Bantu language spoken by a small ethnic community in Nigeria.
E1529329 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: Jaku language | Statement: [Jarawan languages, hasMember, Jaku language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jaku language
Context triple: [Jarawan languages, hasMember, Jaku language]
  • A. Hiaki language
    Hiaki language is an Uto-Aztecan language spoken primarily by the Yaqui (Hiaki) people of northern Mexico and the southwestern United States.
  • B. Jukun language
    The Jukun language is a Niger-Congo language spoken primarily by the Jukun people of central Nigeria, especially in Taraba and surrounding states.
  • C. Jahai language
    The Jahai language is an indigenous Mon–Khmer language spoken by the Jahai people, a small hunter-gatherer community in the Malay Peninsula.
  • D. Aka-Jeru language
    The Aka-Jeru language is an extinct indigenous tongue once spoken by the Aka-Jeru people of the Andaman Islands, belonging to the Ongan branch of the Andamanese language family.
  • E. Wauja language
    The Wauja language is an indigenous Arawakan language spoken by the Wauja people of Brazil’s Upper Xingu region in the Amazon.
  • 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: Jaku language
Triple: [Jarawan languages, hasMember, Jaku language]
Generated description
The Jaku language is a lesser-known Jarawan Bantu language spoken by a small ethnic community in Nigeria.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jaku language
Target entity description: The Jaku language is a lesser-known Jarawan Bantu language spoken by a small ethnic community in Nigeria.
  • A. Hiaki language
    Hiaki language is an Uto-Aztecan language spoken primarily by the Yaqui (Hiaki) people of northern Mexico and the southwestern United States.
  • B. Jukun language
    The Jukun language is a Niger-Congo language spoken primarily by the Jukun people of central Nigeria, especially in Taraba and surrounding states.
  • C. Jahai language
    The Jahai language is an indigenous Mon–Khmer language spoken by the Jahai people, a small hunter-gatherer community in the Malay Peninsula.
  • D. Aka-Jeru language
    The Aka-Jeru language is an extinct indigenous tongue once spoken by the Aka-Jeru people of the Andaman Islands, belonging to the Ongan branch of the Andamanese language family.
  • E. Wauja language
    The Wauja language is an indigenous Arawakan language spoken by the Wauja people of Brazil’s Upper Xingu region in the Amazon.
  • 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_69e11e45fb848190a1b2ae21296e3a5f completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15720fba0819080f6c96f6df4f1e0 completed April 29, 2026, 12:56 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0acc9609788190a1e7306a47a3fb56 completed May 18, 2026, 8:23 a.m.
NEDg Description generation batch_6a0acd67a4c88190bf64d4ecad0491b9 completed May 18, 2026, 8:27 a.m.
NED2 Entity disambiguation (via description) batch_6a0acdcc02ac8190a35b572701410c80 completed May 18, 2026, 8:29 a.m.
Created at: April 16, 2026, 8:41 p.m.