Triple

T22404338
Position Surface form Disambiguated ID Type / Status
Subject Guernsey E553843 entity
Predicate capital P234 FINISHED
Object Saint Peter Port 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: Saint Peter Port | Statement: [Guernsey, capital, Saint Peter Port]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saint Peter Port
Context triple: [Guernsey, capital, Saint Peter Port]
  • A. Saint Peter Port chosen
    Saint Peter Port is the main town and administrative and commercial center of the island of Guernsey in the Channel Islands, known for its historic harbor and picturesque seafront.
  • B. Senglea
    Senglea is a historic fortified city in Malta, renowned for its strategic role and heavy fortifications during the 1565 Great Siege of Malta.
  • C. St Peter Port harbour
    St Peter Port harbour is the main port and picturesque waterfront of Guernsey’s capital, serving as a hub for ferries, yachts, and maritime activity in the Channel Islands.
  • D. Pontal
    Pontal is a municipality in the state of São Paulo, Brazil, located in the Ribeirão Preto metropolitan region.
  • E. Porto-Vecchio
    Porto-Vecchio is a popular seaside resort town in southern Corsica, France, known for its picturesque old port, historic citadel, and nearby white-sand beaches.
  • 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_69e11e4da7048190b4387d422a9a0de5 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f158b6762c8190991fc14c5ca8e609 completed April 29, 2026, 1:02 a.m.
Created at: April 16, 2026, 8:46 p.m.