Triple

T7651856
Position Surface form Disambiguated ID Type / Status
Subject Jonas Gardell E173271 entity
Predicate spouse P13 FINISHED
Object Mark Levengood
Mark Levengood is a Finnish-Swedish television host, journalist, and author known for his warm, humorous style and prominent presence in Swedish media.
 E680296 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: Mark Levengood | Statement: [Jonas Gardell, spouse, Mark Levengood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mark Levengood
Context triple: [Jonas Gardell, spouse, Mark Levengood]
  • A. Mark Kilmer
    Mark Kilmer is the brother of American actor Val Kilmer and a member of the Kilmer family, which has ties to the entertainment industry.
  • B. Pete Schoening
    Pete Schoening was an American mountaineer renowned for his pioneering high-altitude climbs and legendary feats of climbing skill and survival.
  • C. Tom Fry
    Tom Fry is a notable individual who shares the surname Fry and has achieved sufficient recognition to be distinguished among others with that name.
  • D. Ed Gainey
    Ed Gainey is an American politician who became the first Black mayor of Pittsburgh, Pennsylvania.
  • E. Brian Prout
    Brian Prout is an American country music drummer best known as a longtime member of the band Diamond Rio.
  • 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: Mark Levengood
Triple: [Jonas Gardell, spouse, Mark Levengood]
Generated description
Mark Levengood is a Finnish-Swedish television host, journalist, and author known for his warm, humorous style and prominent presence in Swedish media.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mark Levengood
Target entity description: Mark Levengood is a Finnish-Swedish television host, journalist, and author known for his warm, humorous style and prominent presence in Swedish media.
  • A. Mark Kilmer
    Mark Kilmer is the brother of American actor Val Kilmer and a member of the Kilmer family, which has ties to the entertainment industry.
  • B. Pete Schoening
    Pete Schoening was an American mountaineer renowned for his pioneering high-altitude climbs and legendary feats of climbing skill and survival.
  • C. Tom Fry
    Tom Fry is a notable individual who shares the surname Fry and has achieved sufficient recognition to be distinguished among others with that name.
  • D. Ed Gainey
    Ed Gainey is an American politician who became the first Black mayor of Pittsburgh, Pennsylvania.
  • E. Brian Prout
    Brian Prout is an American country music drummer best known as a longtime member of the band Diamond Rio.
  • 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_69c6995473348190a4f41d110d619a18 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c701770ac881909452348c9547ab47 completed March 27, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c89aeb66c081909f3a3d6385637c25 completed March 29, 2026, 3:22 a.m.
NEDg Description generation batch_69c89ed393648190a32cf9267968faf5 completed March 29, 2026, 3:38 a.m.
NED2 Entity disambiguation (via description) batch_69c89f35a7488190a6a9bc3d10bedd5a completed March 29, 2026, 3:40 a.m.
Created at: March 27, 2026, 3:58 p.m.