Triple

T10667485
Position Surface form Disambiguated ID Type / Status
Subject Sula Islands E251393 entity
Predicate hasMainIsland P756 FINISHED
Object Mangole
Mangole is one of the principal islands of Indonesia’s Sula Islands archipelago in North Maluku Province.
 E877536 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: Mangole | Statement: [Sula Islands, hasMainIsland, Mangole]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mangole
Context triple: [Sula Islands, hasMainIsland, Mangole]
  • A. Mbengwi
    Mbengwi is a town in western Cameroon that serves as the administrative center of Momo Division in the country's Northwest Region.
  • B. Bulange
    Bulange is the historic administrative building of the Buganda Kingdom in Kampala, Uganda, serving as the seat of the Lukiiko (parliament) and the Kabaka’s offices.
  • C. Tamba
    Tamba is a city located in Hyogo Prefecture, Japan, known for its rural landscapes, traditional pottery, and historical sites.
  • D. Mberengwa
    Mberengwa is a rural district and growth point in Zimbabwe known for its mining activities and location in the southern part of the Midlands Province.
  • E. Ongwediva
    Ongwediva is a growing town in northern Namibia known as an educational and commercial hub, hosting institutions like the University of Namibia’s campus and the annual Ongwediva Trade Fair.
  • 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: Mangole
Triple: [Sula Islands, hasMainIsland, Mangole]
Generated description
Mangole is one of the principal islands of Indonesia’s Sula Islands archipelago in North Maluku Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mangole
Target entity description: Mangole is one of the principal islands of Indonesia’s Sula Islands archipelago in North Maluku Province.
  • A. Mbengwi
    Mbengwi is a town in western Cameroon that serves as the administrative center of Momo Division in the country's Northwest Region.
  • B. Bulange
    Bulange is the historic administrative building of the Buganda Kingdom in Kampala, Uganda, serving as the seat of the Lukiiko (parliament) and the Kabaka’s offices.
  • C. Tamba
    Tamba is a city located in Hyogo Prefecture, Japan, known for its rural landscapes, traditional pottery, and historical sites.
  • D. Mberengwa
    Mberengwa is a rural district and growth point in Zimbabwe known for its mining activities and location in the southern part of the Midlands Province.
  • E. Ongwediva
    Ongwediva is a growing town in northern Namibia known as an educational and commercial hub, hosting institutions like the University of Namibia’s campus and the annual Ongwediva Trade Fair.
  • 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_69d6aa5b0d2881909584b20efc5877f0 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6f3204bac8190b9bd8bfcc705b06b completed April 9, 2026, 12:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69d97a9ceea08190944354d127f2c73b completed April 10, 2026, 10:33 p.m.
NEDg Description generation batch_69d97df755708190bf71d04ead7eaa2c completed April 10, 2026, 10:47 p.m.
NED2 Entity disambiguation (via description) batch_69d97e96d9888190ba693e1df7eb502d completed April 10, 2026, 10:49 p.m.
Created at: April 8, 2026, 9:08 p.m.