Triple

T7956094
Position Surface form Disambiguated ID Type / Status
Subject San Fernando E184740 entity
Predicate locatedOn P40 FINISHED
Object Isla de León E849065 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: Isla de León | Statement: [San Fernando, locatedOn, Isla de León]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isla de León
Context triple: [San Fernando, locatedOn, Isla de León]
  • A. Isla de León chosen
    Isla de León is a historic island in the Bay of Cádiz in southern Spain, known for its strategic military importance and as the site of the city of San Fernando.
  • B. Isla del Rey
    Isla del Rey is the largest island in Panama’s Pearl Islands archipelago, known for its remote beaches, fishing, and biodiversity in the Gulf of Panama.
  • C. Isla de San Ildefonso
    Isla de San Ildefonso is the former name of Culebra, a small Caribbean island municipality of Puerto Rico known for its beaches and wildlife refuges.
  • D. Isla San Sebastián
    Isla San Sebastián is a small island located within Chile’s Chiloé Archipelago, known for its coastal landscapes and proximity to the traditional culture of Chiloé.
  • E. Isla Islita
    Isla Islita is a small island located within Lake Enriquillo in the Dominican Republic, known for its arid landscape and wildlife such as iguanas and bird species.
  • 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_69ca8292cba881908a64427b938dac47 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3b7d36c081908cc8760a0dbf6001 completed March 31, 2026, 3:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69d59af45f2881908516277f7f625131 completed April 8, 2026, 12:01 a.m.
Created at: March 30, 2026, 5:11 p.m.