Triple

T3363458
Position Surface form Disambiguated ID Type / Status
Subject Viti Levu E70777 entity
Predicate hasPort P35 FINISHED
Object Port of Suva E70078 NE FINISHED

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: Port of Suva | Statement: [Viti Levu, hasPort, Port of Suva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Port of Suva
Context triple: [Viti Levu, hasPort, Port of Suva]
  • A. Port of Suva chosen
    The Port of Suva is Fiji’s principal maritime gateway and busiest commercial harbor, serving as a key hub for regional trade and shipping in the South Pacific.
  • B. Port of Lautoka
    The Port of Lautoka is one of Fiji's main deep-water commercial harbors, serving as a key hub for the country's sugar and general cargo exports in the western part of Viti Levu.
  • C. Port of Honiara
    The Port of Honiara is the main seaport and maritime gateway of the Solomon Islands’ capital, handling the bulk of the country’s international and inter-island shipping.
  • D. Port of Tauranga
    Port of Tauranga is New Zealand’s largest and busiest port, serving as a key international gateway for container and bulk cargo trade.
  • E. Port of Tema
    The Port of Tema is Ghana’s largest and busiest seaport, serving as a major hub for maritime trade and cargo handling in West Africa.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ad85a660c48190998489309a3b4869 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb26a5a508190948932769de0dbb3 completed March 8, 2026, 5:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69b32549eb9c81908c3a525da9eab0aa completed March 12, 2026, 8:42 p.m.
Created at: March 8, 2026, 3:13 p.m.