Triple

T21970878
Position Surface form Disambiguated ID Type / Status
Subject Mia Farrow E542583 entity
Predicate spouse P13 FINISHED
Object Frank Sinatra NE NERFINISHED

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: Frank Sinatra | Statement: [Mia Farrow, spouse, Frank Sinatra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Sinatra
Context triple: [Mia Farrow, spouse, Frank Sinatra]
  • A. Frank Sinatra chosen
    Frank Sinatra was an iconic American singer and actor renowned for his smooth baritone voice, classic pop and jazz recordings, and influential film roles.
  • B. Sinatra
    "Sinatra" is a song by the American alternative metal band Helmet, known for its heavy, riff-driven sound and appearance on their debut album "Strap It On."
  • C. Sinatra
    Sinatra is a lightweight Ruby web application framework known for its simple, DSL-based approach to building web services and APIs.
  • D. Tony Bennett
    Tony Bennett was an American traditional pop and jazz singer renowned for his smooth vocal style and timeless standards like "I Left My Heart in San Francisco."
  • E. Antonino Martino Sinatra
    Antonino Martino Sinatra was an Italian-born immigrant to the United States best known as the father of legendary singer and actor Frank Sinatra.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c48070988190909db97667b9a0ac completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f12484b83081908c08e3285e0b14a9 completed April 28, 2026, 9:20 p.m.
Created at: April 16, 2026, 8:02 p.m.