Triple

T21019902
Position Surface form Disambiguated ID Type / Status
Subject Tha Crossroads E517777 entity
Predicate writer P1360 FINISHED
Object Steven Howse
Steven Howse, better known as Layzie Bone, is an American rapper and member of the hip hop group Bone Thugs-n-Harmony.
E1463003 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: Steven Howse | Statement: [Tha Crossroads, writer, Steven Howse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steven Howse
Context triple: [Tha Crossroads, writer, Steven Howse]
  • A. Brian Howes
    Brian Howes is a Canadian songwriter and record producer known for his work on rock and post-grunge hits, including co-writing Hinder’s breakout single "Lips of an Angel."
  • B. Michael Howells
    Michael Howells was the son of English composer Herbert Howells, to whose memory the choral work "Hymnus Paradisi" is dedicated.
  • C. Tim Howes
    Tim Howes is an American computer scientist and entrepreneur best known as the co-inventor of the LDAP protocol and a co-founder of the cloud services company Loudcloud (later Opsware).
  • D. Jack Howes
    Jack Howes is a family member of the late English actress and singer Sally Ann Howes.
  • E. Peter Howells
    Peter Howells is a notable individual who shares the surname Howells and has achieved sufficient recognition to be distinguished as a bearer of that name.
  • 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: Steven Howse
Triple: [Tha Crossroads, writer, Steven Howse]
Generated description
Steven Howse, better known as Layzie Bone, is an American rapper and member of the hip hop group Bone Thugs-n-Harmony.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Steven Howse
Target entity description: Steven Howse, better known as Layzie Bone, is an American rapper and member of the hip hop group Bone Thugs-n-Harmony.
  • A. Brian Howes
    Brian Howes is a Canadian songwriter and record producer known for his work on rock and post-grunge hits, including co-writing Hinder’s breakout single "Lips of an Angel."
  • B. Michael Howells
    Michael Howells was the son of English composer Herbert Howells, to whose memory the choral work "Hymnus Paradisi" is dedicated.
  • C. Tim Howes
    Tim Howes is an American computer scientist and entrepreneur best known as the co-inventor of the LDAP protocol and a co-founder of the cloud services company Loudcloud (later Opsware).
  • D. Jack Howes
    Jack Howes is a family member of the late English actress and singer Sally Ann Howes.
  • E. Peter Howells
    Peter Howells is a notable individual who shares the surname Howells and has achieved sufficient recognition to be distinguished as a bearer of that name.
  • 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_69e0b50262b081909bc488937145eb73 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc5c905c8190ba2f9f82b6cd1648 completed April 21, 2026, 4:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a093b67103081908033c57e586afa69 completed May 17, 2026, 3:52 a.m.
NEDg Description generation batch_6a0940b362388190a78a244eafa7cbba completed May 17, 2026, 4:14 a.m.
NED2 Entity disambiguation (via description) batch_6a09414912d88190b7da0186ef7b227f completed May 17, 2026, 4:17 a.m.
Created at: April 16, 2026, 1:54 p.m.