Triple

T10667486
Position Surface form Disambiguated ID Type / Status
Subject Sula Islands E251393 entity
Predicate hasMainIsland P756 FINISHED
Object Sanana
Sanana is the principal island and administrative center of the Sula Islands group in North Maluku, Indonesia.
 E877537 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: Sanana | Statement: [Sula Islands, hasMainIsland, Sanana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sanana
Context triple: [Sula Islands, hasMainIsland, Sanana]
  • A. Sanaig
    Sanaig is a core single malt Scotch whisky expression from Islay’s Kilchoman distillery, known for its balance of bourbon and sherry cask influence with a characteristically smoky, coastal profile.
  • B. Kandia
    Kandia is a remote valley and settlement area located within Pakistan’s Kohistan mountain ranges, known for its rugged terrain and isolated communities.
  • C. Yassa
    Yassa was the codified legal and administrative code traditionally attributed to Genghis Khan that governed the Mongol Empire and its successor states.
  • D. Sidama
    Sidama is an ethnic group primarily inhabiting the Sidama Region of southern Ethiopia, known for its distinct Cushitic language and coffee-growing culture.
  • E. Kabaena
    Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly landscapes.
  • 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: Sanana
Triple: [Sula Islands, hasMainIsland, Sanana]
Generated description
Sanana is the principal island and administrative center of the Sula Islands group in North Maluku, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sanana
Target entity description: Sanana is the principal island and administrative center of the Sula Islands group in North Maluku, Indonesia.
  • A. Sanaig
    Sanaig is a core single malt Scotch whisky expression from Islay’s Kilchoman distillery, known for its balance of bourbon and sherry cask influence with a characteristically smoky, coastal profile.
  • B. Kandia
    Kandia is a remote valley and settlement area located within Pakistan’s Kohistan mountain ranges, known for its rugged terrain and isolated communities.
  • C. Yassa
    Yassa was the codified legal and administrative code traditionally attributed to Genghis Khan that governed the Mongol Empire and its successor states.
  • D. Sidama
    Sidama is an ethnic group primarily inhabiting the Sidama Region of southern Ethiopia, known for its distinct Cushitic language and coffee-growing culture.
  • E. Kabaena
    Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly landscapes.
  • 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.