Triple

T23048746
Position Surface form Disambiguated ID Type / Status
Subject Ugljan E573950 entity
Predicate hasSettlement P1068 FINISHED
Object Lukoran
Lukoran is a small coastal village on the Croatian island of Ugljan, known for its tranquil beaches, traditional stone houses, and Mediterranean scenery.
 E1568862 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: Lukoran | Statement: [Ugljan, hasSettlement, Lukoran]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lukoran
Context triple: [Ugljan, hasSettlement, Lukoran]
  • A. Luga
    Luga is a small historic town in northwestern Russia known for its strategic location and role in regional transport and industry.
  • B. Lanckorona
    Lanckorona is a historic village in southern Poland known for its well-preserved wooden architecture and picturesque hillside setting.
  • C. Lakowe
    Lakowe is a suburban community in Lagos State, Nigeria, situated along the Lekki–Epe corridor and known for its growing residential estates and golf resort developments.
  • D. Lanke
    Lanke is a village and district within the municipality of Wandlitz in the state of Brandenburg, Germany.
  • E. Lanke
    Lanke is a poetic nickname for the Chinese city of Quzhou, often associated with its cultural heritage and scenic landscapes.
  • 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: Lukoran
Triple: [Ugljan, hasSettlement, Lukoran]
Generated description
Lukoran is a small coastal village on the Croatian island of Ugljan, known for its tranquil beaches, traditional stone houses, and Mediterranean scenery.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lukoran
Target entity description: Lukoran is a small coastal village on the Croatian island of Ugljan, known for its tranquil beaches, traditional stone houses, and Mediterranean scenery.
  • A. Luga
    Luga is a small historic town in northwestern Russia known for its strategic location and role in regional transport and industry.
  • B. Lanckorona
    Lanckorona is a historic village in southern Poland known for its well-preserved wooden architecture and picturesque hillside setting.
  • C. Lakowe
    Lakowe is a suburban community in Lagos State, Nigeria, situated along the Lekki–Epe corridor and known for its growing residential estates and golf resort developments.
  • D. Lanke
    Lanke is a village and district within the municipality of Wandlitz in the state of Brandenburg, Germany.
  • E. Lanke
    Lanke is a poetic nickname for the Chinese city of Quzhou, often associated with its cultural heritage and scenic landscapes.
  • 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_69e245b9c11481909d06c872214d21af completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1867a206c81909ff923cbf56f7787 completed April 29, 2026, 4:18 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c0ade221081909d25033a5edc73ca completed May 19, 2026, 7:01 a.m.
NEDg Description generation batch_6a0c0f3fe0d081908b86806ec2399eca completed May 19, 2026, 7:20 a.m.
NED2 Entity disambiguation (via description) batch_6a0c0fd3f8608190879a222a697716bd completed May 19, 2026, 7:23 a.m.
Created at: April 17, 2026, 3:54 p.m.