Triple

T20797787
Position Surface form Disambiguated ID Type / Status
Subject Karo language E511956 entity
Predicate glottologName P6521 FINISHED
Object Karo Batak
Karo Batak is an Austronesian language spoken by the Karo people of North Sumatra, Indonesia.
 E1456165 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: Karo Batak | Statement: [Karo language, glottologName, Karo Batak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Karo Batak
Context triple: [Karo language, glottologName, Karo Batak]
  • A. Batak
    The Batak are a group of closely related indigenous ethnic communities from North Sumatra, Indonesia, known for their distinct languages, traditional houses, and rich cultural and ritual practices.
  • B. Toba Batak
    Toba Batak is an Austronesian language spoken primarily by the Toba Batak people of North Sumatra, Indonesia.
  • C. Carakan
    Carakan is the traditional Javanese writing system used for the Javanese language and related regional languages of Indonesia.
  • D. Batak block
    The Batak block is a range of Unicode characters used to represent the traditional Batak scripts of North Sumatra, Indonesia, in digital text.
  • E. Balige
    Balige is a town in North Sumatra, Indonesia, known as an administrative and cultural center near Lake Toba.
  • 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: Karo Batak
Triple: [Karo language, glottologName, Karo Batak]
Generated description
Karo Batak is an Austronesian language spoken by the Karo people of North Sumatra, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Karo Batak
Target entity description: Karo Batak is an Austronesian language spoken by the Karo people of North Sumatra, Indonesia.
  • A. Batak
    The Batak are a group of closely related indigenous ethnic communities from North Sumatra, Indonesia, known for their distinct languages, traditional houses, and rich cultural and ritual practices.
  • B. Toba Batak
    Toba Batak is an Austronesian language spoken primarily by the Toba Batak people of North Sumatra, Indonesia.
  • C. Carakan
    Carakan is the traditional Javanese writing system used for the Javanese language and related regional languages of Indonesia.
  • D. Batak block
    The Batak block is a range of Unicode characters used to represent the traditional Batak scripts of North Sumatra, Indonesia, in digital text.
  • E. Balige
    Balige is a town in North Sumatra, Indonesia, known as an administrative and cultural center near Lake Toba.
  • 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_69e0b4cc69f481908e98751e697b9df4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2ae2c4c819087f620df31dc1aba completed April 21, 2026, 12:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0918bc01588190b12722d6cd9b1f4a completed May 17, 2026, 1:24 a.m.
NEDg Description generation batch_6a0919608d148190aaf1abee12fe8935 completed May 17, 2026, 1:26 a.m.
NED2 Entity disambiguation (via description) batch_6a0919f58008819097e05a187ed4b3de completed May 17, 2026, 1:29 a.m.
Created at: April 16, 2026, 12:39 p.m.