Triple

T1350815
Position Surface form Disambiguated ID Type / Status
Subject Mayan languages E28875 entity
Predicate includesLanguage P2177 FINISHED
Object Akatek
Akatek is a Mayan language spoken primarily by indigenous communities in the highlands of Guatemala.
E166217 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: Akatek | Statement: [Mayan languages, includesLanguage, Akatek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akatek
Context triple: [Mayan languages, includesLanguage, Akatek]
  • A. Acolhua
    The Acolhua were a Nahua-speaking Mesoamerican people of central Mexico, closely allied with the Aztecs and centered in the city-state of Texcoco.
  • B. Tepanec
    The Tepanec were a powerful Nahua-speaking people of central Mexico who dominated the Valley of Mexico before being defeated by the Aztec-led Triple Alliance in the 15th century.
  • C. Huastec
    Huastec is a Mayan language spoken by the Huastec people primarily in northeastern Mexico, especially in parts of Veracruz and neighboring states.
  • D. Mexica
    The Mexica were a Nahuatl-speaking indigenous people of central Mexico who founded the Aztec capital of Tenochtitlan and became the dominant power in the Aztec Empire.
  • E. Totonac
    Totonac is an indigenous language family of eastern Mexico, traditionally spoken by the Totonac people primarily in the states of Veracruz and Puebla.
  • 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: Akatek
Triple: [Mayan languages, includesLanguage, Akatek]
Generated description
Akatek is a Mayan language spoken primarily by indigenous communities in the highlands of Guatemala.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Akatek
Target entity description: Akatek is a Mayan language spoken primarily by indigenous communities in the highlands of Guatemala.
  • A. Acolhua
    The Acolhua were a Nahua-speaking Mesoamerican people of central Mexico, closely allied with the Aztecs and centered in the city-state of Texcoco.
  • B. Tepanec
    The Tepanec were a powerful Nahua-speaking people of central Mexico who dominated the Valley of Mexico before being defeated by the Aztec-led Triple Alliance in the 15th century.
  • C. Huastec
    Huastec is a Mayan language spoken by the Huastec people primarily in northeastern Mexico, especially in parts of Veracruz and neighboring states.
  • D. Mexica
    The Mexica were a Nahuatl-speaking indigenous people of central Mexico who founded the Aztec capital of Tenochtitlan and became the dominant power in the Aztec Empire.
  • E. Totonac
    Totonac is an indigenous language family of eastern Mexico, traditionally spoken by the Totonac people primarily in the states of Veracruz and Puebla.
  • 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_69a498571d248190a0ac9eb02d97097f completed March 1, 2026, 7:49 p.m.
NER Named-entity recognition batch_69a4c26981d081909ca3b8d8cdf7cf2e completed March 1, 2026, 10:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad08a7ed5c8190b9f99a6f4524eae8 completed March 8, 2026, 5:27 a.m.
NEDg Description generation batch_69ad0bbf5d748190ae09c951d0bab9b6 completed March 8, 2026, 5:40 a.m.
NED2 Entity disambiguation (via description) batch_69ad0c18e35481909c19c6888b322d78 completed March 8, 2026, 5:41 a.m.
Created at: March 1, 2026, 7:56 p.m.