Triple

T18037413
Position Surface form Disambiguated ID Type / Status
Subject Suva–Nausori corridor E431546 entity
Predicate connects P390 FINISHED
Object Suva NE NERFINISHED

How this triple was built (2 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: Suva | Statement: [Suva–Nausori corridor, connects, Suva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Suva
Context triple: [Suva–Nausori corridor, connects, Suva]
  • A. Nukuʻalofa
    Nukuʻalofa is the capital and largest city of Tonga, located on the island of Tongatapu in the South Pacific.
  • B. Suva, Fiji chosen
    Suva, Fiji is the capital and largest city of Fiji, serving as a major political, economic, and regional administrative hub in the South Pacific.
  • C. Apia
    Apia is the capital and largest city of Samoa, serving as its main political, economic, and cultural hub on the island of Upolu.
  • D. Apia
    Apia is an Australian insurance brand specializing in products and services tailored primarily for people over 50.
  • E. Honiara
    Honiara is the capital and largest city of the Solomon Islands, located on the island of Guadalcanal in the southwestern Pacific Ocean.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9050fb48190890155145deb0a66 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4be3bc3208190a6db569e79f06232 completed April 19, 2026, 11:36 a.m.
Created at: April 10, 2026, 10:25 a.m.