Triple

T7261251
Position Surface form Disambiguated ID Type / Status
Subject Aru languages E159656 entity
Predicate hasMember P10 FINISHED
Object Koba language (Aru)
Koba language (Aru) is an Austronesian language spoken on the Aru Islands in eastern Indonesia.
 E159656 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: Koba language (Aru) | Statement: [Aru languages, hasMember, Koba language (Aru)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Koba language (Aru)
Context triple: [Aru languages, hasMember, Koba language (Aru)]
  • A. Kaba language
    The Kaba language is a Central Sudanic language spoken primarily in parts of Chad and the Central African Republic by Kaba ethnic groups.
  • B. Aru languages
    Aru languages are a group of closely related Austronesian languages spoken primarily on the Aru Islands in eastern Indonesia.
  • C. Arogbo language
    Arogbo language is a Niger-Congo language spoken by the Arogbo Ijaw people of Nigeria’s Niger Delta region.
  • D. Kogi language
    Kogi is an indigenous Chibchan language spoken by the Kogi people in the Sierra Nevada de Santa Marta region of northern Colombia.
  • E. Kaxabu language
    The Kaxabu language is an indigenous Formosan language of Taiwan spoken by the Kaxabu people and considered highly endangered.
  • 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: Koba language (Aru)
Triple: [Aru languages, hasMember, Koba language (Aru)]
Generated description
Koba language (Aru) is an Austronesian language spoken on the Aru Islands in eastern Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Koba language (Aru)
Target entity description: Koba language (Aru) is an Austronesian language spoken on the Aru Islands in eastern Indonesia.
  • A. Kaba language
    The Kaba language is a Central Sudanic language spoken primarily in parts of Chad and the Central African Republic by Kaba ethnic groups.
  • B. Aru languages chosen
    Aru languages are a group of closely related Austronesian languages spoken primarily on the Aru Islands in eastern Indonesia.
  • C. Arogbo language
    Arogbo language is a Niger-Congo language spoken by the Arogbo Ijaw people of Nigeria’s Niger Delta region.
  • D. Kogi language
    Kogi is an indigenous Chibchan language spoken by the Kogi people in the Sierra Nevada de Santa Marta region of northern Colombia.
  • E. Kaxabu language
    The Kaxabu language is an indigenous Formosan language of Taiwan spoken by the Kaxabu people and considered highly endangered.
  • F. None of above.

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_69c68838f9948190875fd60b2351230c completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6eac79fd081909274aa10ffb192aa completed March 27, 2026, 8:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7d3bda4808190810f2d170cb693b9 completed March 28, 2026, 1:12 p.m.
NEDg Description generation batch_69c7d469fd0081908943099685f94c8b completed March 28, 2026, 1:15 p.m.
NED2 Entity disambiguation (via description) batch_69c7d52299108190974a2e62d6f96610 completed March 28, 2026, 1:18 p.m.
Created at: March 27, 2026, 2:57 p.m.