Triple

T18986028
Position Surface form Disambiguated ID Type / Status
Subject Mafra National Palace E464560 entity
Predicate locatedIn P40 FINISHED
Object Centro Histórico de Mafra NE NERFINISHED

How this triple was built (3 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: Centro Histórico de Mafra | Statement: [Mafra National Palace, locatedIn, Centro Histórico de Mafra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Centro Histórico de Mafra
Context triple: [Mafra National Palace, locatedIn, Centro Histórico de Mafra]
  • A. Tapada Nacional de Mafra
    Tapada Nacional de Mafra is a historic walled royal hunting estate and forest park in Mafra, Portugal, known for its rich biodiversity, wildlife, and outdoor recreational activities.
  • B. Centro Histórico de Sintra
    Centro Histórico de Sintra is the historic center of Sintra, Portugal, renowned for its romantic architecture, palaces, and UNESCO World Heritage status.
  • C. Mafra National Palace
    Mafra National Palace is a vast Baroque royal complex in Mafra, Portugal, renowned for its grand basilica, monumental convent, and one of Europe’s most important historic libraries.
  • D. Royal Palace of Sintra
    The Royal Palace of Sintra is a historic Portuguese royal residence renowned for its distinctive blend of Gothic, Manueline, Moorish, and Mudéjar architectural styles, set in the scenic hills of Sintra.
  • E. Palácio do Campo das Princesas
    Palácio do Campo das Princesas is the historic seat of the government of the state of Pernambuco, located in the city of Recife, Brazil.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Centro Histórico de Mafra
Target entity description: Centro Histórico de Mafra is the historic core of the town of Mafra in Portugal, known for its architectural heritage, traditional urban fabric, and cultural significance surrounding the Mafra National Palace.
  • A. Tapada Nacional de Mafra
    Tapada Nacional de Mafra is a historic walled royal hunting estate and forest park in Mafra, Portugal, known for its rich biodiversity, wildlife, and outdoor recreational activities.
  • B. Centro Histórico de Sintra
    Centro Histórico de Sintra is the historic center of Sintra, Portugal, renowned for its romantic architecture, palaces, and UNESCO World Heritage status.
  • C. Mafra National Palace
    Mafra National Palace is a vast Baroque royal complex in Mafra, Portugal, renowned for its grand basilica, monumental convent, and one of Europe’s most important historic libraries.
  • D. Royal Palace of Sintra
    The Royal Palace of Sintra is a historic Portuguese royal residence renowned for its distinctive blend of Gothic, Manueline, Moorish, and Mudéjar architectural styles, set in the scenic hills of Sintra.
  • E. Palácio do Campo das Princesas
    Palácio do Campo das Princesas is the historic seat of the government of the state of Pernambuco, located in the city of Recife, Brazil.
  • F. None of above. chosen

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_69d8dd008af48190a97ff1c6488edf1b completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d65f7f08819088f56e8e030851b1 completed April 20, 2026, 7:31 a.m.
Created at: April 10, 2026, 12:01 p.m.