Triple

T13864583
Position Surface form Disambiguated ID Type / Status
Subject Sangirese people E333288 entity
Predicate ethnonym P4709 FINISHED
Object Sangirese
Sangirese are an indigenous Austronesian ethnic group native to the Sangihe Islands in North Sulawesi, Indonesia, known for their distinct language and maritime culture.
 E1066565 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: Sangirese | Statement: [Sangirese people, ethnonym, Sangirese]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sangirese
Context triple: [Sangirese people, ethnonym, Sangirese]
  • A. Sanglechi
    Sanglechi is a lesser-known Eastern Iranian language spoken in parts of northeastern Afghanistan and adjacent regions.
  • B. Singida
    Singida is a regional town in central Tanzania known as an important administrative and transport hub.
  • C. Bukindo
    Bukindo is a settlement located within Ukerewe District in Tanzania’s Mwanza Region.
  • D. Sanyati
    Sanyati is a small town in Zimbabwe known for its agricultural activities and location within Mashonaland West Province.
  • E. Kasangulu
    Kasangulu is a town and transport hub in western Democratic Republic of the Congo, located near Kinshasa and known for its position along key road and rail routes.
  • 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: Sangirese
Triple: [Sangirese people, ethnonym, Sangirese]
Generated description
Sangirese are an indigenous Austronesian ethnic group native to the Sangihe Islands in North Sulawesi, Indonesia, known for their distinct language and maritime culture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sangirese
Target entity description: Sangirese are an indigenous Austronesian ethnic group native to the Sangihe Islands in North Sulawesi, Indonesia, known for their distinct language and maritime culture.
  • A. Sanglechi
    Sanglechi is a lesser-known Eastern Iranian language spoken in parts of northeastern Afghanistan and adjacent regions.
  • B. Singida
    Singida is a regional town in central Tanzania known as an important administrative and transport hub.
  • C. Bukindo
    Bukindo is a settlement located within Ukerewe District in Tanzania’s Mwanza Region.
  • D. Sanyati
    Sanyati is a small town in Zimbabwe known for its agricultural activities and location within Mashonaland West Province.
  • E. Kasangulu
    Kasangulu is a town and transport hub in western Democratic Republic of the Congo, located near Kinshasa and known for its position along key road and rail routes.
  • 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_69d81c5ced9c8190b0e9bcc6effe5959 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de05c30d9c81908217d41a3b4aaf85 completed April 14, 2026, 9:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c10113288190b799126d934df92a completed May 3, 2026, 9:41 p.m.
NEDg Description generation batch_69f7c1e7efd88190ac07472647da69e7 completed May 3, 2026, 9:45 p.m.
NED2 Entity disambiguation (via description) batch_69f7c33c2f34819084502d5f03f09ddd completed May 3, 2026, 9:50 p.m.
Created at: April 9, 2026, 10:14 p.m.