Triple

T1209611
Position Surface form Disambiguated ID Type / Status
Subject Palazzo Madama E25967 entity
Predicate locatedNear P294 FINISHED
Object Palazzo Montecitorio E25667 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: Palazzo Montecitorio | Statement: [Palazzo Madama, locatedNear, Palazzo Montecitorio]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Palazzo Montecitorio
Context triple: [Palazzo Madama, locatedNear, Palazzo Montecitorio]
  • A. Palazzo Montecitorio chosen
    Palazzo Montecitorio is a historic Baroque palace in Rome that serves as the seat of the Italian Chamber of Deputies.
  • B. Palazzo Chigi
    Palazzo Chigi is a historic palace in central Rome that serves as the official residence and workplace of the Prime Minister of Italy.
  • C. Palazzo Senatorio
    Palazzo Senatorio is a historic Renaissance-era palace in Rome that serves as the seat of the city’s municipal government on the Capitoline Hill.
  • D. Palazzo della Consulta
    Palazzo della Consulta is an 18th-century Baroque palace in Rome that serves as the seat of Italy’s Constitutional Court.
  • E. Quirinal Palace
    The Quirinal Palace is a historic former papal and royal residence in Rome that now serves as the official residence of the President of the Italian Republic.
  • 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_69a4942b30f08190a91c60573e16b5ef completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bde30ce08190ab60a181ad2d321d completed March 1, 2026, 10:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac8319d0e88190977a4d434b209f11 completed March 7, 2026, 7:57 p.m.
Created at: March 1, 2026, 7:46 p.m.