Triple

T5117914
Position Surface form Disambiguated ID Type / Status
Subject Likan Antai E115382 entity
Predicate language P15 FINISHED
Object Kunza E131839 NE FINISHED

How this triple was built (2 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: Kunza | Statement: [Likan Antai, language, Kunza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kunza
Context triple: [Likan Antai, language, Kunza]
  • A. Kunza chosen
    Kunza is an extinct indigenous language once spoken by the Atacameño (Likan Antai) people of northern Chile’s Atacama Desert region.
  • B. Kąⁿza
    Kąⁿza is the self-designated name (autonym) of the Kaw people, a Native American tribe of the central United States historically associated with present-day Kansas and Oklahoma.
  • C. Hunza
    Hunza is a mountainous valley and popular tourist destination in northern Pakistan, renowned for its dramatic Karakoram scenery and traditionally long-lived local population.
  • D. Hunza
    Hunza was the principal city and political center of the Zaque rulers within the pre-Columbian Muisca Confederation in what is now central Colombia.
  • E. Káⁿza
    Káⁿza is the endonym for the Kansa (Kaw) language, a Siouan language traditionally spoken by the Kansa people of the central United States.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd4442ade0819087b9461f892b206b completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd77ce1ea48190b283cae7bb9b72eb completed March 20, 2026, 4:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69bec4a6a7988190b9beec3f0d9494d1 completed March 21, 2026, 4:17 p.m.
Created at: March 20, 2026, 1:41 p.m.