Triple

T17834316
Position Surface form Disambiguated ID Type / Status
Subject Cilento E445342 entity
Predicate contains P35 FINISHED
Object Paestum 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: Paestum | Statement: [Cilento, contains, Paestum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paestum
Context triple: [Cilento, contains, Paestum]
  • A. Paestum chosen
    Paestum is an ancient Greek and later Roman city in southern Italy renowned for its exceptionally well-preserved Doric Greek temples and archaeological remains.
  • B. Metapontum
    Metapontum was an important ancient Greek city in southern Italy, known for its fertile land, temples, and role within the colonies of Magna Graecia.
  • C. Tarquinia
    Tarquinia is an ancient Etruscan city in central Italy renowned for its richly painted tombs and significant archaeological remains.
  • D. Nuceria Alfaterna
    Nuceria Alfaterna was an ancient Oscan city in southern Italy, notable in Roman times for its strategic location in Campania and its role in regional conflicts.
  • E. Baiae
    Baiae was an ancient Roman resort town on the Bay of Naples famed for its luxurious villas, thermal baths, and popularity among the Roman elite.
  • 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_69d8b9f1a6d881909f024bc603111cdb completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e48d2635a081909d4d48d22e260f8e completed April 19, 2026, 8:07 a.m.
Created at: April 10, 2026, 10:15 a.m.