Triple

T19752874
Position Surface form Disambiguated ID Type / Status
Subject Ati people E474425 entity
Predicate language P15 FINISHED
Object Ati language
The Ati language is an Austronesian language spoken by the indigenous Ati people of the Philippines, particularly on Panay Island.
E1394469 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: Ati language | Statement: [Ati people, language, Ati language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ati language
Context triple: [Ati people, language, Ati language]
  • A. Attié language
    The Attié language is a Niger-Congo language spoken primarily by the Attié people of southern Côte d'Ivoire.
  • B. Atorada language
    The Atorada language is an indigenous Arawakan language of South America, closely associated with the Wapishana people and now highly endangered or possibly extinct.
  • C. Atoni language
    The Atoni language, also known as Dawan, is an Austronesian language spoken primarily by the Atoni people of West Timor in Indonesia.
  • D. Tai Aiton language
    The Tai Aiton language is a Southwestern Tai language spoken by the Tai Aiton ethnic community in northeastern India, particularly in Assam.
  • E. Atta languages
    Atta languages are a group of closely related Austronesian languages spoken by the Atta people in northern Luzon in the Philippines.
  • 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: Ati language
Triple: [Ati people, language, Ati language]
Generated description
The Ati language is an Austronesian language spoken by the indigenous Ati people of the Philippines, particularly on Panay Island.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ati language
Target entity description: The Ati language is an Austronesian language spoken by the indigenous Ati people of the Philippines, particularly on Panay Island.
  • A. Attié language
    The Attié language is a Niger-Congo language spoken primarily by the Attié people of southern Côte d'Ivoire.
  • B. Atorada language
    The Atorada language is an indigenous Arawakan language of South America, closely associated with the Wapishana people and now highly endangered or possibly extinct.
  • C. Atoni language
    The Atoni language, also known as Dawan, is an Austronesian language spoken primarily by the Atoni people of West Timor in Indonesia.
  • D. Tai Aiton language
    The Tai Aiton language is a Southwestern Tai language spoken by the Tai Aiton ethnic community in northeastern India, particularly in Assam.
  • E. Atta languages
    Atta languages are a group of closely related Austronesian languages spoken by the Atta people in northern Luzon in the Philippines.
  • 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_69d8e51940a0819087bd2996f98da668 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6529bcb8c8190bcca61a53be86757 completed April 20, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07bd64ff708190bf23345b53ad6d0d completed May 16, 2026, 12:42 a.m.
NEDg Description generation batch_6a07bf15a6908190b28415ca89f1b43a completed May 16, 2026, 12:49 a.m.
NED2 Entity disambiguation (via description) batch_6a07bfb095b08190a23710cf78a2b923 completed May 16, 2026, 12:52 a.m.
Created at: April 10, 2026, 1:48 p.m.