Triple

T15944997
Position Surface form Disambiguated ID Type / Status
Subject Aari E386661 entity
Predicate hasAlternativeName P39 FINISHED
Object South Aari
South Aari is a dialect or regional variety of the Aari language spoken by the Aari people of southwestern Ethiopia.
E1185222 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: South Aari | Statement: [Aari, hasAlternativeName, South Aari]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: South Aari
Context triple: [Aari, hasAlternativeName, South Aari]
  • A. Aroona
    Aroona is a coastal suburb on Queensland’s Sunshine Coast in Australia, known for its residential character and proximity to beaches and local amenities.
  • B. Arida
    Arida is a city in Japan known for its agricultural production, particularly high-quality citrus fruits, within Wakayama Prefecture.
  • C. Unaaha
    Unaaha is a town in Indonesia that serves as an administrative and population center within the province of Southeast Sulawesi.
  • D. Arunaa
    Arunaa is an alternative spelling or variant form of the name Aruna, which is of Sanskrit origin and often associated with the reddish glow of dawn.
  • E. Nainwa
    Nainwa is a town in the Bundi district of Rajasthan, India, known for its traditional Rajasthani culture and regional markets.
  • 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: South Aari
Triple: [Aari, hasAlternativeName, South Aari]
Generated description
South Aari is a dialect or regional variety of the Aari language spoken by the Aari people of southwestern Ethiopia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: South Aari
Target entity description: South Aari is a dialect or regional variety of the Aari language spoken by the Aari people of southwestern Ethiopia.
  • A. Aroona
    Aroona is a coastal suburb on Queensland’s Sunshine Coast in Australia, known for its residential character and proximity to beaches and local amenities.
  • B. Arida
    Arida is a city in Japan known for its agricultural production, particularly high-quality citrus fruits, within Wakayama Prefecture.
  • C. Unaaha
    Unaaha is a town in Indonesia that serves as an administrative and population center within the province of Southeast Sulawesi.
  • D. Arunaa
    Arunaa is an alternative spelling or variant form of the name Aruna, which is of Sanskrit origin and often associated with the reddish glow of dawn.
  • E. Nainwa
    Nainwa is a town in the Bundi district of Rajasthan, India, known for its traditional Rajasthani culture and regional markets.
  • 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_69d86da882448190a82ea962fe343b79 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156d0d55c8190af59ff169e8add78 completed April 16, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5beabbc8190977f14c1b3ccdf29 completed May 9, 2026, 10:31 p.m.
NEDg Description generation batch_69ffb677927c8190bd45e7bae5fcf1ed completed May 9, 2026, 10:34 p.m.
NED2 Entity disambiguation (via description) batch_69ffb7468fb88190a56cf1df5bd20f63 completed May 9, 2026, 10:37 p.m.
Created at: April 10, 2026, 4:53 a.m.