Triple

T18846602
Position Surface form Disambiguated ID Type / Status
Subject Fort St Angelo E460932 entity
Predicate locatedIn P40 FINISHED
Object Grand Harbour 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: Grand Harbour | Statement: [Fort St Angelo, locatedIn, Grand Harbour]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grand Harbour
Context triple: [Fort St Angelo, locatedIn, Grand Harbour]
  • A. Grand Harbour chosen
    Grand Harbour is a large natural harbour on the eastern coast of Malta, historically significant as a strategic naval base and the maritime gateway to the capital city, Valletta.
  • B. Grand Harbour
    Grand Harbour is a small coastal community on Grand Manan Island in New Brunswick, Canada, known for its fishing activities and maritime character.
  • C. Kingstown Harbour
    Kingstown Harbour is the main seaport and natural harbor serving Kingstown and the island nation of Saint Vincent and the Grenadines.
  • D. Outer Harbour
    Outer Harbour is a section of Sovereign Harbour in Eastbourne, England, primarily used for maritime access and berthing of vessels.
  • E. Outer Harbour
    Outer Harbour is the seaward section of Victoria Harbour, encompassing the more exposed, deep-water approaches used by larger vessels entering and leaving the port.
  • 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_69d8dcfa11e4819090ab1ef5bdcd2b2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5b8efafdc81909608b8a47deeaa8e completed April 20, 2026, 5:26 a.m.
Created at: April 10, 2026, 11:56 a.m.