Triple

T14018297
Position Surface form Disambiguated ID Type / Status
Subject Deià E337256 entity
Predicate partOf P40 FINISHED
Object Mallorca island E23149 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: Mallorca island | Statement: [Deià, partOf, Mallorca island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mallorca island
Context triple: [Deià, partOf, Mallorca island]
  • A. Mallorca chosen
    Mallorca is the largest of Spain’s Balearic Islands, renowned for its Mediterranean beaches, rugged limestone mountains, and historic towns such as Palma.
  • B. Minorca
    Minorca is one of Spain’s Balearic Islands in the Mediterranean Sea, known for its natural harbors, beaches, and historical strategic importance.
  • C. Pla de Mallorca
    Pla de Mallorca is a central inland comarca (county) on the island of Mallorca in Spain, characterized by its rural landscapes, traditional villages, and agricultural economy.
  • D. Balearic Islands
    The Balearic Islands are a Mediterranean archipelago and popular Spanish tourist destination known for islands such as Mallorca, Menorca, Ibiza, and Formentera.
  • E. Formentera
    Formentera is a small Balearic Island in the Mediterranean Sea, renowned for its pristine white-sand beaches, crystal-clear waters, and laid-back atmosphere.
  • 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_69d81c6543a48190bd5ba93d7419e797 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2f3b5b088190a58715779d2c46a6 completed April 14, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb653fedc81908cdd0dde2d3f3329 completed May 7, 2026, 3:57 p.m.
Created at: April 9, 2026, 10:19 p.m.