Triple

T20797583
Position Surface form Disambiguated ID Type / Status
Subject Mayor of Suva E511950 entity
Predicate jurisdiction P82 FINISHED
Object city of 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: city of Suva | Statement: [Mayor of Suva, jurisdiction, city of Suva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: city of Suva
Context triple: [Mayor of Suva, jurisdiction, city of Suva]
  • A. 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.
  • B. Suva City Council Chambers
    Suva City Council Chambers is the main municipal government building and administrative center for the city of Suva, Fiji.
  • C. Suva municipal authorities
    Suva municipal authorities are the local government body responsible for administering and providing public services within the city of Suva, Fiji’s capital.
  • D. Nukuʻalofa
    Nukuʻalofa is the capital and largest city of Tonga, located on the island of Tongatapu in the South Pacific.
  • E. Greater Suva region
    The Greater Suva region is the wider metropolitan and suburban area surrounding Fiji’s capital city, encompassing its main residential, commercial, and industrial zones.
  • 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_69e0b4cc69f481908e98751e697b9df4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2ae2c4c819087f620df31dc1aba completed April 21, 2026, 12:19 a.m.
Created at: April 16, 2026, 12:39 p.m.