Triple

T1728499
Position Surface form Disambiguated ID Type / Status
Subject Oto-Manguean languages E37554 entity
Predicate hasMemberLanguage P7390 FINISHED
Object Ixcatec
Ixcatec is an indigenous Oto-Manguean language of Mexico spoken by a very small and endangered community in Oaxaca.
E235476 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: Ixcatec | Statement: [Oto-Manguean languages, hasMemberLanguage, Ixcatec]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ixcatec
Context triple: [Oto-Manguean languages, hasMemberLanguage, Ixcatec]
  • A. Akatek
    Akatek is a Mayan language spoken primarily by indigenous communities in the highlands of Guatemala.
  • B. Huastec
    Huastec is a Mayan language spoken by the Huastec people primarily in northeastern Mexico, especially in parts of Veracruz and neighboring states.
  • C. 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.
  • D. 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.
  • E. Popoloca
    Popoloca is an indigenous language of central Mexico belonging to the Oto-Manguean family and spoken by the Popoloca people of 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: Ixcatec
Triple: [Oto-Manguean languages, hasMemberLanguage, Ixcatec]
Generated description
Ixcatec is an indigenous Oto-Manguean language of Mexico spoken by a very small and endangered community in Oaxaca.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ixcatec
Target entity description: Ixcatec is an indigenous Oto-Manguean language of Mexico spoken by a very small and endangered community in Oaxaca.
  • A. Akatek
    Akatek is a Mayan language spoken primarily by indigenous communities in the highlands of Guatemala.
  • B. Huastec
    Huastec is a Mayan language spoken by the Huastec people primarily in northeastern Mexico, especially in parts of Veracruz and neighboring states.
  • C. 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.
  • D. 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.
  • E. Popoloca
    Popoloca is an indigenous language of central Mexico belonging to the Oto-Manguean family and spoken by the Popoloca people of 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_69a8861acab88190bb43cde203429399 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa637da7048190a06f2eec6cb87f70 completed March 6, 2026, 5:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae303ee60c819093a70e0e6a431c01 completed March 9, 2026, 2:28 a.m.
NEDg Description generation batch_69ae3418924081909556938e4628ba08 completed March 9, 2026, 2:44 a.m.
NED2 Entity disambiguation (via description) batch_69ae3495fe348190a8dde305ba1df046 completed March 9, 2026, 2:46 a.m.
Created at: March 4, 2026, 7:30 p.m.