Triple

T3679680
Position Surface form Disambiguated ID Type / Status
Subject Rovinj E78079 entity
Predicate hasNearbyIsland P970 FINISHED
Object Sveta Katarina
Sveta Katarina is a small Adriatic island near the Croatian coastal town of Rovinj, known for its scenic beaches, clear waters, and resort facilities.
 E380697 NE FINISHED

How this triple was built (4 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: Sveta Katarina | Statement: [Rovinj, hasNearbyIsland, Sveta Katarina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sveta Katarina
Context triple: [Rovinj, hasNearbyIsland, Sveta Katarina]
  • A. Doroteja
    Doroteja is a feminine given name, commonly used in Slavic countries, that is a variant of the name Dorothea.
  • B. Neša
    Neša is the ancient name of the city of Kültepe, a major Bronze Age trading center and early Hittite capital in central Anatolia.
  • C. Marić
    Marić is the Serbian family name of Mileva Marić, a pioneering physicist and mathematician known for her association with Albert Einstein.
  • D. Rositsa
    Rositsa is a river in northern Bulgaria that serves as a significant tributary of the Yantra River.
  • E. Olivera Despina
    Olivera Despina was a Serbian princess of the Lazarević dynasty who became an Ottoman sultana through her marriage to Sultan Bayezid I.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sveta Katarina
Triple: [Rovinj, hasNearbyIsland, Sveta Katarina]
Generated description
Sveta Katarina is a small Adriatic island near the Croatian coastal town of Rovinj, known for its scenic beaches, clear waters, and resort facilities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sveta Katarina
Target entity description: Sveta Katarina is a small Adriatic island near the Croatian coastal town of Rovinj, known for its scenic beaches, clear waters, and resort facilities.
  • A. Doroteja
    Doroteja is a feminine given name, commonly used in Slavic countries, that is a variant of the name Dorothea.
  • B. Neša
    Neša is the ancient name of the city of Kültepe, a major Bronze Age trading center and early Hittite capital in central Anatolia.
  • C. Marić
    Marić is the Serbian family name of Mileva Marić, a pioneering physicist and mathematician known for her association with Albert Einstein.
  • D. Rositsa
    Rositsa is a river in northern Bulgaria that serves as a significant tributary of the Yantra River.
  • E. Olivera Despina
    Olivera Despina was a Serbian princess of the Lazarević dynasty who became an Ottoman sultana through her marriage to Sultan Bayezid I.
  • F. None of above. chosen

Provenance (5 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_69ad85e18c1c8190be8aafb227f39f48 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc49039308190b33082e2b58aa5cf completed March 8, 2026, 6:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4c3ae61908190beefd0df317b5eca completed March 14, 2026, 2:10 a.m.
NEDg Description generation batch_69b4c79cc8148190af8abfb393232a60 completed March 14, 2026, 2:27 a.m.
NED2 Entity disambiguation (via description) batch_69b4c94ccb5c819092d1ab8246e44108 completed March 14, 2026, 2:34 a.m.
Created at: March 8, 2026, 3:25 p.m.