Triple

T23068443
Position Surface form Disambiguated ID Type / Status
Subject Martina Franca E575121 entity
Predicate subregion P747 FINISHED
Object Salento 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: Salento | Statement: [Martina Franca, subregion, Salento]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Salento
Context triple: [Martina Franca, subregion, Salento]
  • A. Salento chosen
    Salento is a peninsula in southern Apulia, Italy, known for its historic towns, distinctive culture, and scenic Adriatic and Ionian coastlines.
  • B. Salento
    Salento is a picturesque Colombian town in the Andean region, famed for its coffee culture, colorful architecture, and proximity to the Cocora Valley with its towering wax palms.
  • C. Calabrian coast
    The Calabrian coast is the scenic and varied shoreline of Italy’s Calabria region, known for its rugged cliffs, sandy beaches, and clear Tyrrhenian and Ionian waters.
  • D. Basilicata coast
    The Basilicata coast is a short stretch of southern Italian shoreline known for its quiet beaches, rugged landscapes, and views over the Ionian Sea.
  • E. Apulia
    Apulia is a region in southeastern Italy forming the heel of the Italian "boot," known for its ancient Greek heritage, whitewashed hill towns, olive groves, and Adriatic coastline.
  • 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_69e245bd6e4c8190bb8942245b68cad5 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f189a5aa4081909b3f0dc92877323d completed April 29, 2026, 4:31 a.m.
Created at: April 17, 2026, 3:55 p.m.