Triple

T8010353
Position Surface form Disambiguated ID Type / Status
Subject Haʻapai E186472 entity
Predicate hasIsland P970 FINISHED
Object Kotu
Kotu is a small inhabited island in the Haʻapai group of the Kingdom of Tonga, known for its traditional Tongan village life and remote, low-lying coral landscape.
 E707325 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: Kotu | Statement: [Haʻapai, hasIsland, Kotu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kotu
Context triple: [Haʻapai, hasIsland, Kotu]
  • A. Kugu
    Kugu is an Aboriginal Australian language group traditionally associated with the Aurukun region of western Cape York Peninsula in Queensland.
  • B. Kurō
    Kurō is an honorific name historically associated with the famed Japanese military commander Minamoto no Yoshitsune of the late Heian period.
  • C. Kotěra
    Kotěra is a Czech surname most notably associated with Jan Kotěra, a pioneering architect of modern architecture in Central Europe.
  • D. Kote
    Kote is a Georgian given name commonly used as a diminutive of Konstantine.
  • E. Tavuki
    Tavuki is a coastal village located on Kadavu Island in Fiji, known for its traditional Fijian community and surrounding natural beauty.
  • 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: Kotu
Triple: [Haʻapai, hasIsland, Kotu]
Generated description
Kotu is a small inhabited island in the Haʻapai group of the Kingdom of Tonga, known for its traditional Tongan village life and remote, low-lying coral landscape.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kotu
Target entity description: Kotu is a small inhabited island in the Haʻapai group of the Kingdom of Tonga, known for its traditional Tongan village life and remote, low-lying coral landscape.
  • A. Kugu
    Kugu is an Aboriginal Australian language group traditionally associated with the Aurukun region of western Cape York Peninsula in Queensland.
  • B. Kurō
    Kurō is an honorific name historically associated with the famed Japanese military commander Minamoto no Yoshitsune of the late Heian period.
  • C. Kotěra
    Kotěra is a Czech surname most notably associated with Jan Kotěra, a pioneering architect of modern architecture in Central Europe.
  • D. Kote
    Kote is a Georgian given name commonly used as a diminutive of Konstantine.
  • E. Tavuki
    Tavuki is a coastal village located on Kadavu Island in Fiji, known for its traditional Fijian community and surrounding natural beauty.
  • 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_69ca82abaffc8190ab8af79cdbc31ab3 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3d70caf8819090a9f98025470c0d completed March 31, 2026, 3:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc56a54e8081908208b57b7390cc95 completed March 31, 2026, 11:20 p.m.
NEDg Description generation batch_69cc58ecd0608190ab0880992bc203fb completed March 31, 2026, 11:29 p.m.
NED2 Entity disambiguation (via description) batch_69cc5cb791b48190bd5004b518d23f84 completed March 31, 2026, 11:45 p.m.
Created at: March 30, 2026, 5:19 p.m.