Triple

T12838537
Position Surface form Disambiguated ID Type / Status
Subject Shelly Peiken E306982 entity
Predicate wroteForArtist P2831 FINISHED
Object Brandy E5593 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: Brandy | Statement: [Shelly Peiken, wroteForArtist, Brandy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brandy
Context triple: [Shelly Peiken, wroteForArtist, Brandy]
  • A. Brandy
    Brandy is the loyal and well-trained pit bull owned by stuntman Cliff Booth in Quentin Tarantino’s film "Once Upon a Time in Hollywood."
  • B. Brandy chosen
    Brandy is an American R&B singer, songwriter, and actress known for her distinctive vocal style and hits such as "The Boy Is Mine" and "Have You Ever?".
  • C. Brandy Gold
    Brandy Gold is an American former child actress and talent agent, known for her roles in 1980s television and film and for being part of a family of performers.
  • D. Southern Comfort
    Southern Comfort is a 1981 action-thriller film about a group of National Guard soldiers lost in the Louisiana bayou who are hunted by local Cajuns after a violent misunderstanding.
  • E. Bénédictine
    Bénédictine is a French herbal liqueur made from a secret blend of botanicals, known for its sweet, spiced flavor and use in classic cocktails.
  • 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_69d7bdf52b94819096d6f0ba4ab50a98 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96ff11b4481909fb2f92c46186853 completed April 10, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f68edd30e881909062e8f91f614990 completed May 2, 2026, 11:55 p.m.
Created at: April 9, 2026, 5:35 p.m.