Triple

T7767747
Position Surface form Disambiguated ID Type / Status
Subject Vavaʻu E178991 entity
Predicate hasIsland P970 FINISHED
Object Hunga
Hunga is a small volcanic island in the Vavaʻu island group of northern Tonga in the South Pacific Ocean.
 E687253 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: Hunga | Statement: [Vavaʻu, hasIsland, Hunga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hunga
Context triple: [Vavaʻu, hasIsland, Hunga]
  • A. Ronga
    Ronga is a Bantu language spoken primarily in southern Mozambique, known for contributing vocabulary and structural features to African varieties of Portuguese.
  • B. Kapingamarangi
    Kapingamarangi is a remote Micronesian atoll whose people and culture are classified as Polynesian outliers despite its location outside the main Polynesian Triangle.
  • C. Tungag
    Tungag is an Austronesian language spoken in Papua New Guinea, particularly associated with communities in the New Ireland region.
  • D. Onehunga
    Onehunga is a suburb of Auckland, New Zealand, known for its diverse multicultural community and strong Pacific Island, particularly Tongan, presence.
  • E. Tahuata
    Tahuata is a small, rugged island in the southern Marquesas archipelago of French Polynesia, known for its traditional Polynesian culture and remote, scenic 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: Hunga
Triple: [Vavaʻu, hasIsland, Hunga]
Generated description
Hunga is a small volcanic island in the Vavaʻu island group of northern Tonga in the South Pacific Ocean.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hunga
Target entity description: Hunga is a small volcanic island in the Vavaʻu island group of northern Tonga in the South Pacific Ocean.
  • A. Ronga
    Ronga is a Bantu language spoken primarily in southern Mozambique, known for contributing vocabulary and structural features to African varieties of Portuguese.
  • B. Kapingamarangi
    Kapingamarangi is a remote Micronesian atoll whose people and culture are classified as Polynesian outliers despite its location outside the main Polynesian Triangle.
  • C. Tungag
    Tungag is an Austronesian language spoken in Papua New Guinea, particularly associated with communities in the New Ireland region.
  • D. Onehunga
    Onehunga is a suburb of Auckland, New Zealand, known for its diverse multicultural community and strong Pacific Island, particularly Tongan, presence.
  • E. Tahuata
    Tahuata is a small, rugged island in the southern Marquesas archipelago of French Polynesia, known for its traditional Polynesian culture and remote, scenic 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_69c69f30602c819082ab52cd4af5c592 completed March 27, 2026, 3:16 p.m.
NER Named-entity recognition batch_69c70435b7f88190a5e68e6ae701c58f completed March 27, 2026, 10:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8c7e4976c81909ff34dcdcae96999 completed March 29, 2026, 6:34 a.m.
NEDg Description generation batch_69c8c8b75b848190a67de2040d563f86 completed March 29, 2026, 6:37 a.m.
NED2 Entity disambiguation (via description) batch_69c8c941814081909d299df5cd714c71 completed March 29, 2026, 6:40 a.m.
Created at: March 27, 2026, 4:11 p.m.