Triple

T4069629
Position Surface form Disambiguated ID Type / Status
Subject Mam E86612 entity
Predicate hasNeighboringLanguage P16383 FINISHED
Object Akateko
Akateko is a Mayan language spoken primarily by the Akateko people in the western highlands of Guatemala and parts of southern Mexico.
E411186 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: Akateko | Statement: [Mam, hasNeighboringLanguage, Akateko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akateko
Context triple: [Mam, hasNeighboringLanguage, Akateko]
  • A. Aku Uka
    Aku Uka is the paramount traditional monarch of the Jukun people, historically associated with the ancient Kwararafa kingdom in present-day Taraba State, Nigeria.
  • B. Agutaynen
    Agutaynen is an Austronesian language spoken by the Agutaynen people in the Philippines, primarily in the province of Palawan.
  • C. Aku Aku
    Aku Aku is a sentient wooden mask who guides and protects Crash Bandicoot throughout the Crash Bandicoot video game series.
  • D. Akoko
    Akoko is a prominent Yoruba sub-ethnic group in southwestern Nigeria, primarily inhabiting the northeastern part of Ondo State and parts of neighboring states.
  • E. Akpabuyo
    Akpabuyo is a coastal local government area in southeastern Nigeria known for its location near Calabar in Cross River State.
  • 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: Akateko
Triple: [Mam, hasNeighboringLanguage, Akateko]
Generated description
Akateko is a Mayan language spoken primarily by the Akateko people in the western highlands of Guatemala and parts of southern Mexico.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Akateko
Target entity description: Akateko is a Mayan language spoken primarily by the Akateko people in the western highlands of Guatemala and parts of southern Mexico.
  • A. Aku Uka
    Aku Uka is the paramount traditional monarch of the Jukun people, historically associated with the ancient Kwararafa kingdom in present-day Taraba State, Nigeria.
  • B. Agutaynen
    Agutaynen is an Austronesian language spoken by the Agutaynen people in the Philippines, primarily in the province of Palawan.
  • C. Aku Aku
    Aku Aku is a sentient wooden mask who guides and protects Crash Bandicoot throughout the Crash Bandicoot video game series.
  • D. Akoko
    Akoko is a prominent Yoruba sub-ethnic group in southwestern Nigeria, primarily inhabiting the northeastern part of Ondo State and parts of neighboring states.
  • E. Akpabuyo
    Akpabuyo is a coastal local government area in southeastern Nigeria known for its location near Calabar in Cross River State.
  • 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_69aed93ebe448190a1f1686e28740ac9 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefbfa45c88190b7b13b35de816378 completed March 9, 2026, 4:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69b562b6eb708190a7f60192d8df9a27 completed March 14, 2026, 1:29 p.m.
NEDg Description generation batch_69b5668984988190bb4239df9e283142 completed March 14, 2026, 1:45 p.m.
NED2 Entity disambiguation (via description) batch_69b566ea87f88190ad03e548de53553f completed March 14, 2026, 1:47 p.m.
Created at: March 9, 2026, 3:38 p.m.