Triple

T17049469
Position Surface form Disambiguated ID Type / Status
Subject Čiovo E413654 entity
Predicate hasSettlement P1068 FINISHED
Object Žedno
Žedno is a small village located on the Croatian island of Čiovo, known for its traditional Dalmatian character and proximity to the historic town of Trogir.
 E1248376 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: Žedno | Statement: [Čiovo, hasSettlement, Žedno]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Žedno
Context triple: [Čiovo, hasSettlement, Žedno]
  • A. Jedovnice
    Jedovnice is a village in the South Moravian Region of the Czech Republic, known as a recreational center and gateway to the Moravian Karst area.
  • B. Nečas
    Nečas is a Czech surname most notably borne by Petr Nečas, a former Prime Minister of the Czech Republic.
  • C. Podyjí
    Podyjí is a protected national park area in the Czech Republic known for its deep Dyje River valley, diverse ecosystems, and well-preserved natural landscapes.
  • D. Z Boku
    Z Boku is a monumental abstract sculpture by artist Ursula von Rydingsvard, known for her large-scale, textured cedar-wood forms.
  • E. Zavet
    Zavet is a small town and municipal center located in northeastern Bulgaria.
  • 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: Žedno
Triple: [Čiovo, hasSettlement, Žedno]
Generated description
Žedno is a small village located on the Croatian island of Čiovo, known for its traditional Dalmatian character and proximity to the historic town of Trogir.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Žedno
Target entity description: Žedno is a small village located on the Croatian island of Čiovo, known for its traditional Dalmatian character and proximity to the historic town of Trogir.
  • A. Jedovnice
    Jedovnice is a village in the South Moravian Region of the Czech Republic, known as a recreational center and gateway to the Moravian Karst area.
  • B. Nečas
    Nečas is a Czech surname most notably borne by Petr Nečas, a former Prime Minister of the Czech Republic.
  • C. Podyjí
    Podyjí is a protected national park area in the Czech Republic known for its deep Dyje River valley, diverse ecosystems, and well-preserved natural landscapes.
  • D. Z Boku
    Z Boku is a monumental abstract sculpture by artist Ursula von Rydingsvard, known for her large-scale, textured cedar-wood forms.
  • E. Zavet
    Zavet is a small town and municipal center located in northeastern Bulgaria.
  • 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_69d886cde3d481908d4d01ba88ba7eb7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3daa092f08190a9e37404a9de662c completed April 18, 2026, 7:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012341b8e88190a2bee865be5ca1c1 completed May 11, 2026, 12:30 a.m.
NEDg Description generation batch_6a012585a1548190a112f55e2d84ccac completed May 11, 2026, 12:40 a.m.
NED2 Entity disambiguation (via description) batch_6a0126536c348190b9b2eadb4969f8c2 completed May 11, 2026, 12:44 a.m.
Created at: April 10, 2026, 5:34 a.m.