Triple

T6183293
Position Surface form Disambiguated ID Type / Status
Subject Kornati National Park E137994 entity
Predicate hasIsland P970 FINISHED
Object Lavsa
Lavsa is a small, uninhabited island in Croatia’s Adriatic Sea, known for its sheltered bay and clear waters popular with boaters and divers.
 E574207 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: Lavsa | Statement: [Kornati National Park, hasIsland, Lavsa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lavsa
Context triple: [Kornati National Park, hasIsland, Lavsa]
  • A. Laja
    Laja is a small Chilean city in the Biobío Region, known for its riverside setting and proximity to the Biobío River.
  • B. Sarazi
    Sarazi is an Indo-Aryan language spoken primarily in the Chenab Valley region of Jammu and Kashmir, India.
  • C. Romsa
    Romsa is the Northern Sami name for Tromsø, a major city in northern Norway known as a cultural and economic hub above the Arctic Circle.
  • D. Lapseki
    Lapseki is a town and district in Çanakkale Province in northwestern Turkey, situated on the Asian shore of the Dardanelles Strait.
  • E. Veroli
    Veroli is a historic hill town in central Italy’s Lazio region, known for its medieval architecture and ancient roots dating back to the Hernici people.
  • 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: Lavsa
Triple: [Kornati National Park, hasIsland, Lavsa]
Generated description
Lavsa is a small, uninhabited island in Croatia’s Adriatic Sea, known for its sheltered bay and clear waters popular with boaters and divers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lavsa
Target entity description: Lavsa is a small, uninhabited island in Croatia’s Adriatic Sea, known for its sheltered bay and clear waters popular with boaters and divers.
  • A. Laja
    Laja is a small Chilean city in the Biobío Region, known for its riverside setting and proximity to the Biobío River.
  • B. Sarazi
    Sarazi is an Indo-Aryan language spoken primarily in the Chenab Valley region of Jammu and Kashmir, India.
  • C. Romsa
    Romsa is the Northern Sami name for Tromsø, a major city in northern Norway known as a cultural and economic hub above the Arctic Circle.
  • D. Lapseki
    Lapseki is a town and district in Çanakkale Province in northwestern Turkey, situated on the Asian shore of the Dardanelles Strait.
  • E. Veroli
    Veroli is a historic hill town in central Italy’s Lazio region, known for its medieval architecture and ancient roots dating back to the Hernici people.
  • 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_69c008a8fd408190b7ec6e42934974a6 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06100c2b0819097f287e86f63d590 completed March 22, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69c141c6b5888190983bff620c7663cc completed March 23, 2026, 1:36 p.m.
NEDg Description generation batch_69c1472997d081909266b0e64fdbfe96 completed March 23, 2026, 1:59 p.m.
NED2 Entity disambiguation (via description) batch_69c147b5214c819082c20480965842be completed March 23, 2026, 2:01 p.m.
Created at: March 22, 2026, 4:19 p.m.