Triple

T16461629
Position Surface form Disambiguated ID Type / Status
Subject Global E399819 entity
Predicate ownsBrand P1500 FINISHED
Object Heart 90s
Heart 90s is a UK digital radio station that plays classic hits from the 1990s as part of the Heart radio network.
E1216931 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: Heart 90s | Statement: [Global, ownsBrand, Heart 90s]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heart 90s
Context triple: [Global, ownsBrand, Heart 90s]
  • A. Heart 80s
    Heart 80s is a UK digital radio station that plays classic hits from the 1980s as part of the Heart radio network.
  • B. Heart 00s
    Heart 00s is a UK digital radio station from the Heart network that focuses on playing popular hits from the 2000s.
  • C. HEART
    HEART is a contemporary art museum in Herning, Denmark, known for its modern architecture and exhibitions of international and Danish contemporary art.
  • D. Only Heart
    Only Heart is a song by John Mayer featured on his 2003 studio album "Heavier Things."
  • E. Internet Hearts
    Internet Hearts is a digital version of the classic trick-avoidance card game Hearts that was bundled with various Microsoft Windows operating systems for online and local play.
  • 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: Heart 90s
Triple: [Global, ownsBrand, Heart 90s]
Generated description
Heart 90s is a UK digital radio station that plays classic hits from the 1990s as part of the Heart radio network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Heart 90s
Target entity description: Heart 90s is a UK digital radio station that plays classic hits from the 1990s as part of the Heart radio network.
  • A. Heart 80s
    Heart 80s is a UK digital radio station that plays classic hits from the 1980s as part of the Heart radio network.
  • B. Heart 00s
    Heart 00s is a UK digital radio station from the Heart network that focuses on playing popular hits from the 2000s.
  • C. HEART
    HEART is a contemporary art museum in Herning, Denmark, known for its modern architecture and exhibitions of international and Danish contemporary art.
  • D. Only Heart
    Only Heart is a song by John Mayer featured on his 2003 studio album "Heavier Things."
  • E. Internet Hearts
    Internet Hearts is a digital version of the classic trick-avoidance card game Hearts that was bundled with various Microsoft Windows operating systems for online and local play.
  • 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_69d87f2dac988190b74d6e185fa88ba4 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32d819d548190bc76a0ec2e223437 completed April 18, 2026, 7:06 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00581a11e881908681f68c26ee6a05 completed May 10, 2026, 10:04 a.m.
NEDg Description generation batch_6a005865b5dc819087b1438a2f148575 completed May 10, 2026, 10:05 a.m.
NED2 Entity disambiguation (via description) batch_6a005900cb1c8190bb05016f3bef0950 completed May 10, 2026, 10:08 a.m.
Created at: April 10, 2026, 5:10 a.m.