Triple

T16448692
Position Surface form Disambiguated ID Type / Status
Subject Stato da Mar E399497 entity
Predicate hasPart P35 FINISHED
Object Famagusta E174472 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: Famagusta | Statement: [Stato da Mar, hasPart, Famagusta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Famagusta
Context triple: [Stato da Mar, hasPart, Famagusta]
  • A. Famagusta chosen
    Famagusta is a historic port city on the eastern coast of Cyprus, known for its medieval architecture, walled old town, and strategic maritime importance.
  • B. Nicosia
    Nicosia is the capital and largest city of Cyprus, known for being the last divided capital in Europe, split between the Greek Cypriot south and Turkish Cypriot north.
  • C. Nicosia
    Nicosia is a historic hill town in central Sicily, Italy, known for its medieval architecture and panoramic views over the surrounding countryside.
  • D. Paphos
    Paphos is an ancient coastal city in Cyprus famed in Greek mythology as a principal cult center and legendary birthplace of the goddess Aphrodite.
  • E. Larnaca
    Larnaca is a coastal city in southeastern Cyprus known for its historic sites, palm-lined seafront, and role as a major tourism and transport hub.
  • 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_69d87f2c6778819080fcfae53be8f12a completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32cdee44c8190ae0df20c58ff7558 completed April 18, 2026, 7:03 a.m.
NED1 Entity disambiguation (via context triple) batch_6a004f4b738881908f8a205466397f33 completed May 10, 2026, 9:26 a.m.
Created at: April 10, 2026, 5:10 a.m.