Triple

T21160998
Position Surface form Disambiguated ID Type / Status
Subject Kanak languages E521438 entity
Predicate includeLanguage P2177 FINISHED
Object Xârâcùù
Xârâcùù is an indigenous Kanak language of New Caledonia, spoken primarily in the region around Canala on the island of Grande Terre.
 E1469704 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: Xârâcùù | Statement: [Kanak languages, includeLanguage, Xârâcùù]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Xârâcùù
Context triple: [Kanak languages, includeLanguage, Xârâcùù]
  • A. Chaxiraxi
    Chaxiraxi is a principal mother-goddess figure in the traditional religion of the Guanche people of the Canary Islands, often associated with fertility, protection, and later syncretized with the Virgin Mary.
  • B. Charuymaq
    Charuymaq is a county-level city in northwestern Iran known for its rural communities and location within East Azerbaijan Province.
  • C. Khara
    Khara is a Japanese animation studio founded by Hideaki Anno, best known for producing the Rebuild of Evangelion film series.
  • D. Xanéu
    Xanéu is an alternative name for the Terena language, an Arawakan language spoken by the Terena people of Brazil.
  • E. Chararic
    Chararic was an early medieval king of the Suebi in Galicia, known primarily from sparse historical references to his rule during the post-Roman period in the Iberian Peninsula.
  • 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: Xârâcùù
Triple: [Kanak languages, includeLanguage, Xârâcùù]
Generated description
Xârâcùù is an indigenous Kanak language of New Caledonia, spoken primarily in the region around Canala on the island of Grande Terre.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Xârâcùù
Target entity description: Xârâcùù is an indigenous Kanak language of New Caledonia, spoken primarily in the region around Canala on the island of Grande Terre.
  • A. Chaxiraxi
    Chaxiraxi is a principal mother-goddess figure in the traditional religion of the Guanche people of the Canary Islands, often associated with fertility, protection, and later syncretized with the Virgin Mary.
  • B. Charuymaq
    Charuymaq is a county-level city in northwestern Iran known for its rural communities and location within East Azerbaijan Province.
  • C. Khara
    Khara is a Japanese animation studio founded by Hideaki Anno, best known for producing the Rebuild of Evangelion film series.
  • D. Xanéu
    Xanéu is an alternative name for the Terena language, an Arawakan language spoken by the Terena people of Brazil.
  • E. Chararic
    Chararic was an early medieval king of the Suebi in Galicia, known primarily from sparse historical references to his rule during the post-Roman period in the Iberian Peninsula.
  • 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_69e0b50d1ea481909c07e63c3ead9316 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e72530e3388190a170c5a2a19dadfc completed April 21, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a096dd03f008190a52d21e17eb8e90e completed May 17, 2026, 7:27 a.m.
NEDg Description generation batch_6a096ef9a6388190ba34cbe01863946c completed May 17, 2026, 7:32 a.m.
NED2 Entity disambiguation (via description) batch_6a096f7706448190a1bb61535e0adcd3 completed May 17, 2026, 7:34 a.m.
Created at: April 16, 2026, 2:59 p.m.