Triple

T9108666
Position Surface form Disambiguated ID Type / Status
Subject Spanish Florida E218539 entity
Predicate hasSettlement P1068 FINISHED
Object St. Marks E392010 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: St. Marks | Statement: [Spanish Florida, hasSettlement, St. Marks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: St. Marks
Context triple: [Spanish Florida, hasSettlement, St. Marks]
  • A. Spanish Point
    Spanish Point is a coastal village in County Clare, Ireland, known for its Atlantic beaches, surfing, and scenic views along the Wild Atlantic Way.
  • B. St. Marks, Florida chosen
    St. Marks, Florida is a small historic coastal city in Wakulla County known for its fishing, boating, and proximity to the St. Marks National Wildlife Refuge.
  • C. Downtown Key West
    Downtown Key West is the lively historic and commercial heart of Key West, Florida, known for its vibrant nightlife, waterfront attractions, and preserved Conch-style architecture.
  • D. South Beach Harbor
    South Beach Harbor is a marina in San Francisco known for its recreational boat berths and proximity to Oracle Park along the city’s eastern waterfront.
  • E. Old Town Margate
    Old Town Margate is the historic heart of the seaside town, known for its cobbled streets, independent galleries, vintage shops, and vibrant café and bar scene.
  • 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_69ca83db7448819090d0a5de842ef2ac completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cca57543448190829853c31e05dd8c completed April 1, 2026, 4:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69d03038dba48190991cb76576349bc3 completed April 3, 2026, 9:25 p.m.
Created at: March 30, 2026, 7:16 p.m.