Triple

T7720891
Position Surface form Disambiguated ID Type / Status
Subject Suwawa language E175005 entity
Predicate hasAlternativeName P39 FINISHED
Object Bonda’
Bonda’ is an alternative name for the Suwawa language, an Austronesian language spoken in parts of northern Sulawesi, Indonesia.
 E683700 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: Bonda’ | Statement: [Suwawa language, hasAlternativeName, Bonda’]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bonda’
Context triple: [Suwawa language, hasAlternativeName, Bonda’]
  • A. Bonda
    Bonda is an archaeological site associated with the pre-Columbian Tairona culture in northern Colombia.
  • B. Bonalu
    Bonalu is a traditional Hindu folk festival of Telangana centered on the worship of the goddess Mahakali, marked by colorful processions, ritual offerings, and regional music and dance.
  • C. Bandiana
    Bandiana is a suburb in the Australian state of Victoria, known primarily for its military facilities and proximity to the regional city of Wodonga.
  • D. Barooga
    Barooga is a small town in southern New South Wales, Australia, known for its Murray River location and recreational attractions such as golf courses and riverfront activities.
  • E. Baniata
    Baniata is an Oceanic language of the Meso-Melanesian group spoken in the Solomon Islands.
  • 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: Bonda’
Triple: [Suwawa language, hasAlternativeName, Bonda’]
Generated description
Bonda’ is an alternative name for the Suwawa language, an Austronesian language spoken in parts of northern Sulawesi, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bonda’
Target entity description: Bonda’ is an alternative name for the Suwawa language, an Austronesian language spoken in parts of northern Sulawesi, Indonesia.
  • A. Bonda
    Bonda is an archaeological site associated with the pre-Columbian Tairona culture in northern Colombia.
  • B. Bonalu
    Bonalu is a traditional Hindu folk festival of Telangana centered on the worship of the goddess Mahakali, marked by colorful processions, ritual offerings, and regional music and dance.
  • C. Bandiana
    Bandiana is a suburb in the Australian state of Victoria, known primarily for its military facilities and proximity to the regional city of Wodonga.
  • D. Barooga
    Barooga is a small town in southern New South Wales, Australia, known for its Murray River location and recreational attractions such as golf courses and riverfront activities.
  • E. Baniata
    Baniata is an Oceanic language of the Meso-Melanesian group spoken in the Solomon Islands.
  • 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_69c6995d541c81909eaa646b1a8369a9 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c702f0366c8190a78f0b03f090fc2c completed March 27, 2026, 10:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8b517c64881908d24e8613dc33bf4 completed March 29, 2026, 5:13 a.m.
NEDg Description generation batch_69c8b5bb46508190b3da11b2f9bf05a6 completed March 29, 2026, 5:16 a.m.
NED2 Entity disambiguation (via description) batch_69c8b65a04a48190bf5e01ba0921cf14 completed March 29, 2026, 5:19 a.m.
Created at: March 27, 2026, 4:05 p.m.