Triple

T8427320
Position Surface form Disambiguated ID Type / Status
Subject Titanium (song) E199033 entity
Predicate vocalist P2000 FINISHED
Object Sia E199040 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: Sia | Statement: [Titanium (song), vocalist, Sia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sia
Context triple: [Titanium (song), vocalist, Sia]
  • A. Sia chosen
    Sia is an Australian singer-songwriter and pop artist known for her powerful vocals, emotive songwriting, and distinctive visual style featuring face-obscuring wigs.
  • B. Imogen Heap
    Imogen Heap is an English singer-songwriter, producer, and audio innovator known for her experimental electronic music and pioneering work with music technology such as the Mi.Mu gloves.
  • C. Emily King
    Emily King is an American singer-songwriter known for her soulful blend of R&B, pop, and jazz influences and her critically acclaimed, Grammy-nominated work.
  • D. Adele Casagrande
    Adele Casagrande was an Italian fashion designer and entrepreneur best known as the co-founder of the luxury fashion house Fendi.
  • E. Robyn
    Robyn is the first given name of global pop and R&B superstar Rihanna, born Robyn Rihanna Fenty.
  • 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_69ca8313c99081909a5c6d83b91de5b3 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbd124378c819086ea2fa6ecbfffe1 completed March 31, 2026, 1:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce1d502c448190aabc957786bde79f completed April 2, 2026, 7:40 a.m.
Created at: March 30, 2026, 6:07 p.m.