Triple

T10765218
Position Surface form Disambiguated ID Type / Status
Subject Niki Taylor E253935 entity
Predicate hasChild P369 FINISHED
Object Viggo Komar
Viggo Komar is one of the children of American supermodel Niki Taylor.
E888576 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: Viggo Komar | Statement: [Niki Taylor, hasChild, Viggo Komar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Viggo Komar
Context triple: [Niki Taylor, hasChild, Viggo Komar]
  • A. Johan Rheborg
    Johan Rheborg is a Swedish actor and comedian best known as a member of the comedy group Killinggänget and for his roles in acclaimed Swedish films and television series.
  • B. Gunnar Wejke
    Gunnar Wejke was a Swedish architect known for co-designing major public buildings, including the multi-purpose arena Scandinavium in Gothenburg.
  • C. Kurt Ludvigsen
    Kurt Ludvigsen is a cinematographer best known for his work on the romantic drama film "Autumn in New York."
  • D. Henrik Uldalen
    Henrik Uldalen is a contemporary Norwegian figurative painter known for his ethereal, dreamlike portraits that blend realism with surreal and abstract elements.
  • E. Nicolai Gädda
    Nicolai Gädda is a renowned Swedish operatic tenor celebrated for his exceptional vocal technique, linguistic versatility, and extensive international recording and performance career in the mid-20th century.
  • 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: Viggo Komar
Triple: [Niki Taylor, hasChild, Viggo Komar]
Generated description
Viggo Komar is one of the children of American supermodel Niki Taylor.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Viggo Komar
Target entity description: Viggo Komar is one of the children of American supermodel Niki Taylor.
  • A. Johan Rheborg
    Johan Rheborg is a Swedish actor and comedian best known as a member of the comedy group Killinggänget and for his roles in acclaimed Swedish films and television series.
  • B. Gunnar Wejke
    Gunnar Wejke was a Swedish architect known for co-designing major public buildings, including the multi-purpose arena Scandinavium in Gothenburg.
  • C. Kurt Ludvigsen
    Kurt Ludvigsen is a cinematographer best known for his work on the romantic drama film "Autumn in New York."
  • D. Henrik Uldalen
    Henrik Uldalen is a contemporary Norwegian figurative painter known for his ethereal, dreamlike portraits that blend realism with surreal and abstract elements.
  • E. Nicolai Gädda
    Nicolai Gädda is a renowned Swedish operatic tenor celebrated for his exceptional vocal technique, linguistic versatility, and extensive international recording and performance career in the mid-20th century.
  • 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_69d6aa5f54f4819082d0bbcb6f8797e6 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d731a5d5248190badfc5a8ab0215d6 completed April 9, 2026, 4:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb0b5c9d8819088edb21a35d8b0dc completed April 14, 2026, 9:25 p.m.
NEDg Description generation batch_69deb3ef9d0c8190816dc99ed102e03d completed April 14, 2026, 9:38 p.m.
NED2 Entity disambiguation (via description) batch_69deb4e471648190a00f3a921b5fb657 completed April 14, 2026, 9:43 p.m.
Created at: April 8, 2026, 9:16 p.m.