Triple

T8808524
Position Surface form Disambiguated ID Type / Status
Subject Suzanne Vega E209595 entity
Predicate notableWork P4 FINISHED
Object Luka
"Luka" is a 1987 folk-pop song by Suzanne Vega that poignantly addresses the subject of child abuse from a child's perspective.
 E760699 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: [Suzanne Vega, notableWork, Luka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Luka
Context triple: [Suzanne Vega, notableWork, 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. Matija
    Matija is a South Slavic given name, equivalent to the English name Matthew.
  • D. Luka Pecel
    Luka Pecel is the husband of American actress Sasha Alexander, known for her roles in television series such as "NCIS" and "Rizzoli & Isles."
  • E. Julijan
    Julijan is a given name, commonly used in Slavic regions, that corresponds to the name Julian.
  • 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: [Suzanne Vega, notableWork, Luka]
Generated description
"Luka" is a 1987 folk-pop song by Suzanne Vega that poignantly addresses the subject of child abuse from a child's perspective.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Luka
Target entity description: "Luka" is a 1987 folk-pop song by Suzanne Vega that poignantly addresses the subject of child abuse from a child's perspective.
  • 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. Matija
    Matija is a South Slavic given name, equivalent to the English name Matthew.
  • D. Luka Pecel
    Luka Pecel is the husband of American actress Sasha Alexander, known for her roles in television series such as "NCIS" and "Rizzoli & Isles."
  • E. Julijan
    Julijan is a given name, commonly used in Slavic regions, that corresponds to the name Julian.
  • 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_69ca8363f3308190a47e3f1ebd51f613 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5fd4cbec8190a929d4e60da8ad65 completed March 31, 2026, 11:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf892b813481909739f72ffd080f49 completed April 3, 2026, 9:32 a.m.
NEDg Description generation batch_69cf8a8c87dc81909d5c0d769341b17c completed April 3, 2026, 9:38 a.m.
NED2 Entity disambiguation (via description) batch_69cf8b79a0b48190a29491f5f8f81217 completed April 3, 2026, 9:42 a.m.
Created at: March 30, 2026, 6:45 p.m.