Triple

T14759995
Position Surface form Disambiguated ID Type / Status
Subject Recanati E346831 entity
Predicate sharesBorderWith P224 FINISHED
Object Loreto E266884 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: Loreto | Statement: [Recanati, sharesBorderWith, Loreto]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Loreto
Context triple: [Recanati, sharesBorderWith, Loreto]
  • A. Loreto
    Loreto is a historic coastal town in Baja California Sur, Mexico, known as one of the earliest Spanish settlements in the region and a gateway to the rich marine life of the Gulf of California.
  • B. Loreto, Italy chosen
    Loreto, Italy is a renowned Catholic pilgrimage town in the Marche region, best known for the Basilica della Santa Casa, which houses the Holy House of Nazareth and a revered Marian shrine.
  • C. San Leonardo
    San Leonardo is a landlocked agricultural municipality in the province of Nueva Ecija in the Philippines, known for its rice farming and rural communities.
  • D. Loretto
    Loretto is a small town in central Kentucky best known as the home of the Maker’s Mark bourbon distillery.
  • E. Loretto
    Loretto is a small city located in Hennepin County in the U.S. state of Minnesota.
  • 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_69d822e8896c819091169882f9b20486 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7f0f5a48190af008352c26574d7 completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0cefb7c08190bf69b15165f046d0 completed May 8, 2026, 4:18 p.m.
Created at: April 10, 2026, 1:30 a.m.