Triple

T1407273
Position Surface form Disambiguated ID Type / Status
Subject Sanaa Lathan E31721 entity
Predicate starredIn P1668 FINISHED
Object Brown Sugar E139144 NE FINISHED

How this triple was built (2 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: Brown Sugar | Statement: [Sanaa Lathan, starredIn, Brown Sugar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brown Sugar
Context triple: [Sanaa Lathan, starredIn, Brown Sugar]
  • A. Brown Sugar chosen
    Brown Sugar is a 2002 romantic comedy-drama film about lifelong friends navigating love and hip-hop in New York City, starring Taye Diggs and Sanaa Lathan.
  • B. Brown Sugar
    "Brown Sugar" is a 1971 rock song by the Rolling Stones, known for its gritty guitar riff, controversial lyrics, and status as one of the band’s signature hits.
  • C. Sugar
    Sugar is a child-friendly, open-source learning platform and graphical interface designed to support education on low-cost laptops like those from the One Laptop per Child project.
  • D. Honey
    "Honey" is a song that served as the lead single for the musical act Butterfly.
  • E. Honey
    Honey is a popular online shopping tool and browser extension that automatically finds and applies coupon codes to help users save money.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a49918e1f88190ba610f9dc8114578 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c3be10348190ade8a73780d2c008 completed March 1, 2026, 10:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad015839908190b7f9f6c79dcc0367 completed March 8, 2026, 4:55 a.m.
Created at: March 1, 2026, 7:59 p.m.