Triple

T18423590
Position Surface form Disambiguated ID Type / Status
Subject Fairport Convention E442078 entity
Predicate notableWork P4 FINISHED
Object 50:50@50
50:50@50 is a live and studio hybrid album by British folk-rock band Fairport Convention, released to celebrate their 50th anniversary.
E1323988 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: 50:50@50 | Statement: [Fairport Convention, notableWork, 50:50@50]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 50:50@50
Context triple: [Fairport Convention, notableWork, 50:50@50]
  • A. 50/50
    50/50 is a 2011 dramedy film starring Joseph Gordon-Levitt and Seth Rogen that follows a young man's emotional and humorous journey after being diagnosed with cancer.
  • B. 50 Pct
    50 Pct is the common abbreviation for the New York City Police Department’s 50th Precinct, which serves the northwest Bronx.
  • C. 50/50 Twin
    50/50 Twin is an American rapper known for his work in the Houston hip hop scene and collaborations with fellow Southern artists.
  • D. C50
    C50 is a popular model of Honda’s Super Cub series of small, fuel-efficient commuter motorcycles, known for their durability and widespread use worldwide.
  • E. Half & Half
    Half & Half is an American sitcom that follows the evolving relationship between two half-sisters with very different upbringings as they navigate family, career, and love in San Francisco.
  • 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: 50:50@50
Triple: [Fairport Convention, notableWork, 50:50@50]
Generated description
50:50@50 is a live and studio hybrid album by British folk-rock band Fairport Convention, released to celebrate their 50th anniversary.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 50:50@50
Target entity description: 50:50@50 is a live and studio hybrid album by British folk-rock band Fairport Convention, released to celebrate their 50th anniversary.
  • A. 50/50
    50/50 is a 2011 dramedy film starring Joseph Gordon-Levitt and Seth Rogen that follows a young man's emotional and humorous journey after being diagnosed with cancer.
  • B. 50 Pct
    50 Pct is the common abbreviation for the New York City Police Department’s 50th Precinct, which serves the northwest Bronx.
  • C. 50/50 Twin
    50/50 Twin is an American rapper known for his work in the Houston hip hop scene and collaborations with fellow Southern artists.
  • D. C50
    C50 is a popular model of Honda’s Super Cub series of small, fuel-efficient commuter motorcycles, known for their durability and widespread use worldwide.
  • E. Half & Half
    Half & Half is an American sitcom that follows the evolving relationship between two half-sisters with very different upbringings as they navigate family, career, and love in San Francisco.
  • 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_69d8b9eb8a508190a942fd75ebd8b1dc completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e51b102dd88190af474902fe58ead5 completed April 19, 2026, 6:12 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03f0a9d0a08190a78610499b1372c9 completed May 13, 2026, 3:31 a.m.
NEDg Description generation batch_6a03f21c622c81909f34f0d3da0c4491 completed May 13, 2026, 3:38 a.m.
NED2 Entity disambiguation (via description) batch_6a03f356e48c81908d74414b736303a4 completed May 13, 2026, 3:43 a.m.
Created at: April 10, 2026, 10:47 a.m.