Triple

T132327
Position Surface form Disambiguated ID Type / Status
Subject Culebra E2678 entity
Predicate locatedWestOf P4239 FINISHED
Object Saint Thomas E4116 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: Saint Thomas | Statement: [Culebra, locatedWestOf, Saint Thomas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saint Thomas
Context triple: [Culebra, locatedWestOf, Saint Thomas]
  • A. Saint Thomas chosen
    Saint Thomas is a major Caribbean island known for its bustling port city of Charlotte Amalie, popular beaches, and role as a tourism and commercial hub of the U.S. Virgin Islands.
  • B. Hamilton, Bermuda
    Hamilton, Bermuda is the capital and primary commercial and administrative center of Bermuda, known for its busy harbor, financial services industry, and role as the territory’s political hub.
  • C. Nassau
    Nassau is the largest city and main commercial and cultural center of the Bahamas, located on New Providence Island.
  • D. St. Helena
    St. Helena is a small, historic city in California’s Napa Valley known for its wineries, vineyards, and upscale culinary and tourism scene.
  • E. Chatham
    Chatham is a coastal town on the southeastern tip of Cape Cod in Massachusetts, known for its beaches, historic lighthouse, and maritime character.
  • 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_69a2520c0f3481908b0ed054a2fca8d0 completed Feb. 28, 2026, 2:25 a.m.
NER Named-entity recognition batch_69a257871b8c8190868838837c0058d6 completed Feb. 28, 2026, 2:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69a3232bf59c8190a8f2478c85b92ac8 completed Feb. 28, 2026, 5:17 p.m.
Created at: Feb. 28, 2026, 2:30 a.m.