Triple

T3996164
Position Surface form Disambiguated ID Type / Status
Subject Talk That Talk E87101 entity
Predicate hasTrack P3284 FINISHED
Object Drunk on Love
"Drunk on Love" is a song by Rihanna from her sixth studio album, blending emotional lyrics with a dance-pop and electronic sound.
E404307 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: Drunk on Love | Statement: [Talk That Talk, hasTrack, Drunk on Love]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Drunk on Love
Context triple: [Talk That Talk, hasTrack, Drunk on Love]
  • A. Drunk in Love
    "Drunk in Love" is a sultry, trap-influenced R&B song by Beyoncé featuring Jay-Z that became one of her signature hits following its release in 2013.
  • B. Drunk on You
    "Drunk on You" is a popular country song by American singer Luke Bryan, known for its romantic, laid-back summer vibe and commercial success on country radio.
  • C. Here’s Love
    "Here’s Love" is a 1963 Broadway musical by Meredith Willson, adapted from the classic film "Miracle on 34th Street."
  • D. Without Love
    "Without Love" is a lively duet-turned-ensemble love song from the musical Hairspray, celebrating young romance and defiance of social barriers.
  • E. One Night of Love
    One Night of Love is a 1934 American romantic musical film starring Grace Moore that became notable for its operatic performances and critical acclaim.
  • 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: Drunk on Love
Triple: [Talk That Talk, hasTrack, Drunk on Love]
Generated description
"Drunk on Love" is a song by Rihanna from her sixth studio album, blending emotional lyrics with a dance-pop and electronic sound.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Drunk on Love
Target entity description: "Drunk on Love" is a song by Rihanna from her sixth studio album, blending emotional lyrics with a dance-pop and electronic sound.
  • A. Drunk in Love
    "Drunk in Love" is a sultry, trap-influenced R&B song by Beyoncé featuring Jay-Z that became one of her signature hits following its release in 2013.
  • B. Drunk on You
    "Drunk on You" is a popular country song by American singer Luke Bryan, known for its romantic, laid-back summer vibe and commercial success on country radio.
  • C. Here’s Love
    "Here’s Love" is a 1963 Broadway musical by Meredith Willson, adapted from the classic film "Miracle on 34th Street."
  • D. Without Love
    "Without Love" is a lively duet-turned-ensemble love song from the musical Hairspray, celebrating young romance and defiance of social barriers.
  • E. One Night of Love
    One Night of Love is a 1934 American romantic musical film starring Grace Moore that became notable for its operatic performances and critical acclaim.
  • 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_69aed94118148190975e6aa4e554cde9 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefa2159d88190a01de8b038341916 completed March 9, 2026, 4:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5403f14ec8190a77189c7066676f2 completed March 14, 2026, 11:02 a.m.
NEDg Description generation batch_69b54112e3788190800e295a745c4689 completed March 14, 2026, 11:05 a.m.
NED2 Entity disambiguation (via description) batch_69b541808d548190987ad1538c647664 completed March 14, 2026, 11:07 a.m.
Created at: March 9, 2026, 3:34 p.m.