Triple

T15653100
Position Surface form Disambiguated ID Type / Status
Subject Sizzla E376360 entity
Predicate notableSong P4 FINISHED
Object Thank U Mamma
"Thank U Mamma" is a popular reggae song by Jamaican artist Sizzla that expresses gratitude and love for mothers and their sacrifices.
 E1169515 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: Thank U Mamma | Statement: [Sizzla, notableSong, Thank U Mamma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Thank U Mamma
Context triple: [Sizzla, notableSong, Thank U Mamma]
  • A. Dear Mama
    "Dear Mama" is a heartfelt 1995 hip-hop song by Tupac Shakur that pays tribute to his mother and is widely regarded as one of his most iconic and emotional works.
  • B. Mama Im Dat Man
    Mama Im Dat Man is a professional NBA 2K League player best known as the standout point guard who earned MVP honors during the league’s 2019 season.
  • C. Momma
    Momma is a track featured on the hip-hop album "Yellow Tape."
  • D. Momma
    "Momma" is a reflective, jazz-infused hip-hop track by Kendrick Lamar from his critically acclaimed album *To Pimp a Butterfly*, exploring themes of identity, home, and self-discovery.
  • E. Sweet Mama
    Sweet Mama is a recurring comedic segment featured in the television game show "Win, Lose or Draw."
  • 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: Thank U Mamma
Triple: [Sizzla, notableSong, Thank U Mamma]
Generated description
"Thank U Mamma" is a popular reggae song by Jamaican artist Sizzla that expresses gratitude and love for mothers and their sacrifices.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Thank U Mamma
Target entity description: "Thank U Mamma" is a popular reggae song by Jamaican artist Sizzla that expresses gratitude and love for mothers and their sacrifices.
  • A. Dear Mama
    "Dear Mama" is a heartfelt 1995 hip-hop song by Tupac Shakur that pays tribute to his mother and is widely regarded as one of his most iconic and emotional works.
  • B. Mama Im Dat Man
    Mama Im Dat Man is a professional NBA 2K League player best known as the standout point guard who earned MVP honors during the league’s 2019 season.
  • C. Momma
    Momma is a track featured on the hip-hop album "Yellow Tape."
  • D. Momma
    "Momma" is a reflective, jazz-infused hip-hop track by Kendrick Lamar from his critically acclaimed album *To Pimp a Butterfly*, exploring themes of identity, home, and self-discovery.
  • E. Sweet Mama
    Sweet Mama is a recurring comedic segment featured in the television game show "Win, Lose or Draw."
  • 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_69d85cd1564c8190991adda63bfab4b0 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ef089948190902ec22f4d7bc932 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6797954c8190ac05ee3db634efa7 completed May 9, 2026, 4:57 p.m.
NEDg Description generation batch_69ff68481ff881909c23ae20bd3a9ff8 completed May 9, 2026, 5 p.m.
NED2 Entity disambiguation (via description) batch_69ff6911a76c819088c8a86d2106b6c6 completed May 9, 2026, 5:04 p.m.
Created at: April 10, 2026, 4:15 a.m.