Triple

T4283591
Position Surface form Disambiguated ID Type / Status
Subject Vanua Levu E97212 entity
Predicate hasTown P847 FINISHED
Object Savusavu
Savusavu is a small coastal town on the island of Vanua Levu in Fiji, known for its sheltered bay, hot springs, and popularity as a yachting and diving destination.
 E426419 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: Savusavu | Statement: [Vanua Levu, hasTown, Savusavu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Savusavu
Context triple: [Vanua Levu, hasTown, Savusavu]
  • A. Tambolaka
    Tambolaka is a town on the Indonesian island of Sumba that serves as an important local hub with an airport and access point for exploring the island.
  • B. Rahaita
    Rahaita is a settlement located in Eritrea's Southern Red Sea Region, along the country's arid Red Sea coastal area.
  • C. Tolitoli
    Tolitoli is a coastal town and regency capital in Central Sulawesi, Indonesia, known as a regional hub for trade and agriculture.
  • D. Nukunonu
    Nukunonu is one of the three atolls of Tokelau in the South Pacific Ocean, serving as an important administrative and population center of the territory.
  • E. Hulhumalé
    Hulhumalé is a reclaimed island and planned urban development in the Maldives, created to expand housing and infrastructure near the capital, Malé.
  • 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: Savusavu
Triple: [Vanua Levu, hasTown, Savusavu]
Generated description
Savusavu is a small coastal town on the island of Vanua Levu in Fiji, known for its sheltered bay, hot springs, and popularity as a yachting and diving destination.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Savusavu
Target entity description: Savusavu is a small coastal town on the island of Vanua Levu in Fiji, known for its sheltered bay, hot springs, and popularity as a yachting and diving destination.
  • A. Tambolaka
    Tambolaka is a town on the Indonesian island of Sumba that serves as an important local hub with an airport and access point for exploring the island.
  • B. Rahaita
    Rahaita is a settlement located in Eritrea's Southern Red Sea Region, along the country's arid Red Sea coastal area.
  • C. Tolitoli
    Tolitoli is a coastal town and regency capital in Central Sulawesi, Indonesia, known as a regional hub for trade and agriculture.
  • D. Nukunonu
    Nukunonu is one of the three atolls of Tokelau in the South Pacific Ocean, serving as an important administrative and population center of the territory.
  • E. Hulhumalé
    Hulhumalé is a reclaimed island and planned urban development in the Maldives, created to expand housing and infrastructure near the capital, Malé.
  • 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_69b3454595848190a0e6bbb6a2bea040 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3503a84548190989a96d1a30d6ef7 completed March 12, 2026, 11:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5b7bec1a88190bd36ed6d48e1c94e completed March 14, 2026, 7:32 p.m.
NEDg Description generation batch_69b5b870a66c8190a59bfc0e99234596 completed March 14, 2026, 7:35 p.m.
NED2 Entity disambiguation (via description) batch_69b5b908fad88190846278c782a10cdb completed March 14, 2026, 7:37 p.m.
Created at: March 12, 2026, 11:07 p.m.