Triple

T1648840
Position Surface form Disambiguated ID Type / Status
Subject Kelis E35644 entity
Predicate single P3283 FINISHED
Object Millionaire E186272 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: Millionaire | Statement: [Kelis, single, Millionaire]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Millionaire
Context triple: [Kelis, single, Millionaire]
  • A. Millionaire chosen
    "Millionaire" is a 2004 R&B/hip-hop single by American singer Kelis featuring André 3000, known for its laid-back groove and distinctive production.
  • B. Million Dollar Bill
    "Million Dollar Bill" is an upbeat dance-pop and R&B song by Whitney Houston, released as a single from her 2009 comeback album "I Look to You."
  • C. How to Steal a Million
    How to Steal a Million is a 1966 romantic comedy heist film starring Audrey Hepburn and Peter O'Toole, centered on an art forgery scheme in Paris.
  • D. Million Dollar Staircase
    The Million Dollar Staircase is an ornate, late-19th-century grand staircase renowned for its elaborate stone carvings and opulent design inside the New York State Capitol in Albany.
  • E. Money Monster
    Money Monster is a 2016 American thriller film about a live financial TV show taken hostage on air, blending media satire with real-time suspense.
  • 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_69a8860568888190a32cd9f70acbba42 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90a6537e0819082b966023e0c0583 completed March 5, 2026, 4:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad681db3408190a3b469e319486419 completed March 8, 2026, 12:14 p.m.
Created at: March 4, 2026, 7:29 p.m.