Triple

T23048706
Position Surface form Disambiguated ID Type / Status
Subject Dugi Otok E573949 entity
Predicate hasSettlement P1068 FINISHED
Object Luka
Luka is a small coastal village and harbor settlement on the Croatian island of Dugi Otok in the Adriatic Sea.
E1568853 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: Luka | Statement: [Dugi Otok, hasSettlement, Luka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Luka
Context triple: [Dugi Otok, hasSettlement, Luka]
  • A. Luka
    Luka is a central character in Maxim Gorky's play "The Lower Depths," known as a compassionate wanderer whose comforting lies and philosophical outlook profoundly affect the other destitute inhabitants of the shelter.
  • B. Luka
    Luka is the young protagonist of Salman Rushdie’s fantasy novel "Luka and the Fire of Life," who embarks on a magical quest to save his father.
  • C. Luka
    "Luka" is a 1987 folk-pop song by Suzanne Vega that poignantly addresses the subject of child abuse from a child's perspective.
  • D. Luka
    Luka is a masculine given name used in various cultures, often as a form of Luke or Lucas.
  • E. Matija
    Matija is a South Slavic given name, equivalent to the English name Matthew.
  • 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: Luka
Triple: [Dugi Otok, hasSettlement, Luka]
Generated description
Luka is a small coastal village and harbor settlement on the Croatian island of Dugi Otok in the Adriatic Sea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Luka
Target entity description: Luka is a small coastal village and harbor settlement on the Croatian island of Dugi Otok in the Adriatic Sea.
  • A. Luka
    Luka is a central character in Maxim Gorky's play "The Lower Depths," known as a compassionate wanderer whose comforting lies and philosophical outlook profoundly affect the other destitute inhabitants of the shelter.
  • B. Luka
    Luka is the young protagonist of Salman Rushdie’s fantasy novel "Luka and the Fire of Life," who embarks on a magical quest to save his father.
  • C. Luka
    "Luka" is a 1987 folk-pop song by Suzanne Vega that poignantly addresses the subject of child abuse from a child's perspective.
  • D. Luka
    Luka is a masculine given name used in various cultures, often as a form of Luke or Lucas.
  • E. Matija
    Matija is a South Slavic given name, equivalent to the English name Matthew.
  • 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.