Triple

T6638032
Position Surface form Disambiguated ID Type / Status
Subject Ngaju language E150506 entity
Predicate hasGlottologName P6521 FINISHED
Object Ngaju
Ngaju is an Austronesian language spoken primarily by the Ngaju Dayak people in Central Kalimantan on the island of Borneo in Indonesia.
 E612417 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: Ngaju | Statement: [Ngaju language, hasGlottologName, Ngaju]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ngaju
Context triple: [Ngaju language, hasGlottologName, Ngaju]
  • A. Napareuli
    Napareuli is a Georgian wine appellation in the Kakheti region, known for producing high-quality wines, particularly from the Saperavi grape.
  • B. Gadjang
    Gadjang is an Aboriginal Australian language variety associated with the Worimi people of New South Wales.
  • C. Upangas
    Upangas are a group of secondary Jain scriptures that elaborate and supplement the teachings found in the primary Agamas.
  • D. Parji
    Parji is a modern Dravidian language spoken in parts of central India, descended from the reconstructed ancestral language Proto-Dravidian.
  • E. Kukawa
    Kukawa is a historic town in northeastern Nigeria that once served as the political and cultural center of the Kanuri people and the Bornu Empire.
  • 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: Ngaju
Triple: [Ngaju language, hasGlottologName, Ngaju]
Generated description
Ngaju is an Austronesian language spoken primarily by the Ngaju Dayak people in Central Kalimantan on the island of Borneo in Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ngaju
Target entity description: Ngaju is an Austronesian language spoken primarily by the Ngaju Dayak people in Central Kalimantan on the island of Borneo in Indonesia.
  • A. Napareuli
    Napareuli is a Georgian wine appellation in the Kakheti region, known for producing high-quality wines, particularly from the Saperavi grape.
  • B. Gadjang
    Gadjang is an Aboriginal Australian language variety associated with the Worimi people of New South Wales.
  • C. Upangas
    Upangas are a group of secondary Jain scriptures that elaborate and supplement the teachings found in the primary Agamas.
  • D. Parji
    Parji is a modern Dravidian language spoken in parts of central India, descended from the reconstructed ancestral language Proto-Dravidian.
  • E. Kukawa
    Kukawa is a historic town in northeastern Nigeria that once served as the political and cultural center of the Kanuri people and the Bornu Empire.
  • 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_69c687f0ceb08190bf40807bfc605fa5 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6aff082b0819089f5a69aa67d5346 completed March 27, 2026, 4:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6f7918c208190924c1906c7886a2c completed March 27, 2026, 9:33 p.m.
NEDg Description generation batch_69c6f86efd00819099d48fe7cb9640a3 completed March 27, 2026, 9:36 p.m.
NED2 Entity disambiguation (via description) batch_69c6f91ac7788190832a133c4fe046f1 completed March 27, 2026, 9:39 p.m.
Created at: March 27, 2026, 2 p.m.