Triple

T24545950
Position Surface form Disambiguated ID Type / Status
Subject New Ireland languages E607224 entity
Predicate haveSubgroup P47820 FINISHED
Object Kara language (New Ireland)
The Kara language of New Ireland is an Austronesian language spoken by indigenous communities on New Ireland island in Papua New Guinea.
E1638260 NE FINISHED

How this triple was built (2 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: Kara language (New Ireland) | Statement: [New Ireland languages, haveSubgroup, Kara language (New Ireland)]
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: Kara language (New Ireland)
Triple: [New Ireland languages, haveSubgroup, Kara language (New Ireland)]
Generated description
The Kara language of New Ireland is an Austronesian language spoken by indigenous communities on New Ireland island in Papua New Guinea.

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_69e2c4c9bf94819082d05da6f5c29907 completed April 17, 2026, 11:39 p.m.
NER Named-entity recognition batch_69f2a8c9ab9c81909ff56f707e3fd27b completed April 30, 2026, 12:56 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0feea8d17c8190912b4efee020af73 completed May 22, 2026, 5:50 a.m.
NEDg Description generation batch_6a0fef6feb088190870b41df1edb338e completed May 22, 2026, 5:53 a.m.
NED2 Entity disambiguation (via description) batch_6a0ff097dd8881908bb83d84a6581ef7 completed May 22, 2026, 5:58 a.m.
Created at: April 18, 2026, 2:27 a.m.