Triple

T782081
Position Surface form Disambiguated ID Type / Status
Subject Epirus E16518 entity
Predicate containsPort P35 FINISHED
Object Preveza E98737 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: Preveza | Statement: [Epirus, containsPort, Preveza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Preveza
Context triple: [Epirus, containsPort, Preveza]
  • A. Preveza chosen
    Preveza is a coastal city in northwestern Greece known for its strategic location at the entrance of the Ambracian Gulf, its historic old town, and nearby beaches.
  • B. Morea
    Morea was the medieval name for the Peloponnese peninsula in southern Greece, which served as a significant Byzantine province and later despotate.
  • C. Otranto
    Otranto is a historic coastal town in southern Italy’s Apulia region, known for its medieval castle, cathedral, and strategic position on the Adriatic Sea.
  • D. Ragusa
    Ragusa is a historic baroque hilltop city in southeastern Sicily, Italy, renowned for its UNESCO-listed old town and distinctive architecture.
  • E. Quarracino
    Quarracino is an Italian-origin surname most notably associated with Argentine Cardinal Antonio Quarracino.
  • 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_69a4936ad1fc81908f190208059ccf78 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a765ba688190ab328bb159583077 completed March 1, 2026, 8:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7a3afbb0c8190b4e7aa7824c8b787 completed March 4, 2026, 3:14 a.m.
Created at: March 1, 2026, 7:37 p.m.