Triple

T7362771
Position Surface form Disambiguated ID Type / Status
Subject Kodava E169791 entity
Predicate alternateName P39 FINISHED
Object Coorgi
Coorgi is an alternate name for the Kodava language spoken by the Kodava people of the Coorg (Kodagu) region in Karnataka, India.
E658094 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: Coorgi | Statement: [Kodava, alternateName, Coorgi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Coorgi
Context triple: [Kodava, alternateName, Coorgi]
  • A. Little Tew
    Little Tew is a small rural village in Oxfordshire, England, known for its traditional stone cottages and picturesque countryside setting.
  • B. Basset
    Basset is a surname and term most commonly associated with the Basset Hound dog breed and with various historical families and individuals bearing that name.
  • C. Kikapoo
    Kikapoo is an alternative name for the Kickapoo language, an Algonquian language spoken by the Kickapoo people in parts of the United States and Mexico.
  • D. Cairn Terrier
    The Cairn Terrier is a small, hardy, and spirited Scottish terrier breed known for its shaggy coat, alert expression, and lively, affectionate personality.
  • E. Pug
    Pug is a high-performance, whitespace-sensitive template engine for Node.js that compiles a concise, indentation-based syntax into HTML for server-side rendering.
  • 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: Coorgi
Triple: [Kodava, alternateName, Coorgi]
Generated description
Coorgi is an alternate name for the Kodava language spoken by the Kodava people of the Coorg (Kodagu) region in Karnataka, India.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Coorgi
Target entity description: Coorgi is an alternate name for the Kodava language spoken by the Kodava people of the Coorg (Kodagu) region in Karnataka, India.
  • A. Little Tew
    Little Tew is a small rural village in Oxfordshire, England, known for its traditional stone cottages and picturesque countryside setting.
  • B. Basset
    Basset is a surname and term most commonly associated with the Basset Hound dog breed and with various historical families and individuals bearing that name.
  • C. Kikapoo
    Kikapoo is an alternative name for the Kickapoo language, an Algonquian language spoken by the Kickapoo people in parts of the United States and Mexico.
  • D. Cairn Terrier
    The Cairn Terrier is a small, hardy, and spirited Scottish terrier breed known for its shaggy coat, alert expression, and lively, affectionate personality.
  • E. Pug
    Pug is a high-performance, whitespace-sensitive template engine for Node.js that compiles a concise, indentation-based syntax into HTML for server-side rendering.
  • 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_69c68a5ade988190885b7175f63b7534 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f15f218081909b5cc7a8cc695055 completed March 27, 2026, 9:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7fab3a9d88190b9193dd0729eba5a completed March 28, 2026, 3:58 p.m.
NEDg Description generation batch_69c7fbe2a86881909be54dac809aa9af completed March 28, 2026, 4:03 p.m.
NED2 Entity disambiguation (via description) batch_69c7fc84fff48190b4b43da21a9ede51 completed March 28, 2026, 4:06 p.m.
Created at: March 27, 2026, 3:06 p.m.