Triple

T19292328
Position Surface form Disambiguated ID Type / Status
Subject Castel del Monte E482473 entity
Predicate locatedIn P40 FINISHED
Object Andria NE NERFINISHED

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: Andria | Statement: [Castel del Monte, locatedIn, Andria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andria
Context triple: [Castel del Monte, locatedIn, Andria]
  • A. Andria chosen
    Andria is a historic city in the Apulia region of southern Italy, known for its proximity to the UNESCO-listed Castel del Monte and its rich medieval heritage.
  • B. Andrada
    Andrada is a Portuguese-language surname most notably associated with Brazilian statesman and independence leader José Bonifácio de Andrada e Silva.
  • C. Doirani
    Doirani is a settlement in northern Greece near Lake Doirani, close to the border with North Macedonia, known for its historical significance in the Balkan Wars and World War I.
  • D. Daulida
    Daulida is an alternative name for the ancient Greek town of Daulis in the region of Phocis.
  • E. Laranda
    Laranda was an important ancient city in the region of Lycaonia in central Anatolia, known from Hellenistic and Roman times.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d8e8cf61b0819096fe3e4107827c4e completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fc819a7881909a7afbd06d9dd3f0 completed April 20, 2026, 10:14 a.m.
Created at: April 10, 2026, 1:31 p.m.