Triple

T23068472
Position Surface form Disambiguated ID Type / Status
Subject Martina Franca E575121 entity
Predicate locatedNear P294 FINISHED
Object Locorotondo 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: Locorotondo | Statement: [Martina Franca, locatedNear, Locorotondo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Locorotondo
Context triple: [Martina Franca, locatedNear, Locorotondo]
  • A. Locorotondo chosen
    Locorotondo is a picturesque hilltop town in Italy’s Apulia region, renowned for its circular historic center, whitewashed houses, and surrounding vineyards.
  • B. Grottaglie
    Grottaglie is an Italian town in the Apulia region renowned for its historic ceramics tradition and characteristic whitewashed old quarter.
  • C. Castelvetrano
    Castelvetrano is a town in western Sicily, Italy, known for its olive production and proximity to the ancient Greek archaeological site of Selinunte.
  • D. Casarano
    Casarano is a town in the Salento area of southern Italy known for its historic architecture, religious festivals, and role as a local commercial and industrial center.
  • E. Barletta
    Barletta is a historic coastal city in the Apulia region of southern Italy, known for its medieval architecture and role as a provincial capital.
  • 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.