Triple

T14633760
Position Surface form Disambiguated ID Type / Status
Subject King's Disease II E343548 entity
Predicate hasPart P35 FINISHED
Object YKTV
YKTV is a track by Nas from his acclaimed hip-hop album "King's Disease II."
E1110647 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: YKTV | Statement: [King's Disease II, hasPart, YKTV]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: YKTV
Context triple: [King's Disease II, hasPart, YKTV]
  • A. YTV
    YTV is a Canadian English-language specialty television channel primarily known for broadcasting children's and youth-oriented programming.
  • B. PewDiePie
    PewDiePie is a Swedish YouTuber and comedian best known for his hugely popular gaming videos and influential presence in online entertainment.
  • C. Vlogbrothers
    Vlogbrothers is a popular YouTube channel and online community project created by brothers John and Hank Green, known for their educational, humorous, and thoughtful video blogs.
  • D. Viddy
    Viddy was a mobile social video-sharing app that allowed users to create, edit, and share short video clips with an online community.
  • E. Bounce TV
    Bounce TV is an American digital multicast television network primarily targeting African American audiences with a mix of movies, original series, and syndicated programming.
  • 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: YKTV
Triple: [King's Disease II, hasPart, YKTV]
Generated description
YKTV is a track by Nas from his acclaimed hip-hop album "King's Disease II."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: YKTV
Target entity description: YKTV is a track by Nas from his acclaimed hip-hop album "King's Disease II."
  • A. YTV
    YTV is a Canadian English-language specialty television channel primarily known for broadcasting children's and youth-oriented programming.
  • B. PewDiePie
    PewDiePie is a Swedish YouTuber and comedian best known for his hugely popular gaming videos and influential presence in online entertainment.
  • C. Vlogbrothers
    Vlogbrothers is a popular YouTube channel and online community project created by brothers John and Hank Green, known for their educational, humorous, and thoughtful video blogs.
  • D. Viddy
    Viddy was a mobile social video-sharing app that allowed users to create, edit, and share short video clips with an online community.
  • E. Bounce TV
    Bounce TV is an American digital multicast television network primarily targeting African American audiences with a mix of movies, original series, and syndicated programming.
  • 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_69d822dffc3c8190aa173b90761bffda completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb4aa7cb48190b008bd6b0e162c89 completed April 14, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69fda933937881909f3cf59fba878dfd completed May 8, 2026, 9:13 a.m.
NEDg Description generation batch_69fdb3efb4fc8190bca7469d89a66a85 completed May 8, 2026, 9:59 a.m.
NED2 Entity disambiguation (via description) batch_69fdb48b5ca08190be61da2fdb7dbce4 completed May 8, 2026, 10:01 a.m.
Created at: April 10, 2026, 1:26 a.m.