Triple

T8938981
Position Surface form Disambiguated ID Type / Status
Subject Tiriyó language E212848 entity
Predicate hasDialects P4251 FINISHED
Object Akuriyó
Akuriyó is a dialect of the Tiriyó language spoken by the Akuriyó people, an Indigenous group of the Guiana region in South America.
E558288 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: Akuriyó | Statement: [Tiriyó language, hasDialects, Akuriyó]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akuriyó
Context triple: [Tiriyó language, hasDialects, Akuriyó]
  • A. Arosi
    Arosi is an Oceanic Austronesian language spoken primarily on Makira Island in the Solomon Islands.
  • B. Urakhi
    Urakhi is a dialect of the Dargin language spoken by a subset of the Dargin people in the North Caucasus region of Russia.
  • C. Okitipupa
    Okitipupa is a prominent town in southwestern Nigeria known as a commercial and administrative center within Ondo State.
  • D. Akawaio
    The Akawaio are an Indigenous people of the Guiana Highlands in Guyana, Venezuela, and Brazil, known for their Cariban language and traditional forest-based way of life.
  • E. Amar'e
    Amar'e is a retired American professional basketball player best known as an explosive All-Star power forward in the NBA, primarily with the Phoenix Suns and New York Knicks.
  • 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: Akuriyó
Triple: [Tiriyó language, hasDialects, Akuriyó]
Generated description
Akuriyó is a dialect of the Tiriyó language spoken by the Akuriyó people, an Indigenous group of the Guiana region in South America.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Akuriyó
Target entity description: Akuriyó is a dialect of the Tiriyó language spoken by the Akuriyó people, an Indigenous group of the Guiana region in South America.
  • A. Arosi
    Arosi is an Oceanic Austronesian language spoken primarily on Makira Island in the Solomon Islands.
  • B. Urakhi
    Urakhi is a dialect of the Dargin language spoken by a subset of the Dargin people in the North Caucasus region of Russia.
  • C. Okitipupa
    Okitipupa is a prominent town in southwestern Nigeria known as a commercial and administrative center within Ondo State.
  • D. Akawaio chosen
    The Akawaio are an Indigenous people of the Guiana Highlands in Guyana, Venezuela, and Brazil, known for their Cariban language and traditional forest-based way of life.
  • E. Amar'e
    Amar'e is a retired American professional basketball player best known as an explosive All-Star power forward in the NBA, primarily with the Phoenix Suns and New York Knicks.
  • F. None of above.

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_69ca839694c88190b324ffeb43d23b08 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc66b7484481909e0d7610552f5386 completed April 1, 2026, 12:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc1eb308c81909f5be133c75ad568 completed April 3, 2026, 1:34 p.m.
NEDg Description generation batch_69cfc24b4fe481909b7c4f58b787a21e completed April 3, 2026, 1:36 p.m.
NED2 Entity disambiguation (via description) batch_69cfc33fbedc8190a8f04ec6f43891f0 completed April 3, 2026, 1:40 p.m.
Created at: March 30, 2026, 6:58 p.m.