Triple

T5163710
Position Surface form Disambiguated ID Type / Status
Subject The Sea Hawk (novel) E116497 entity
Predicate author P4 FINISHED
Object Rafael Sabatini E218744 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: Rafael Sabatini | Statement: [The Sea Hawk (novel), author, Rafael Sabatini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rafael Sabatini
Context triple: [The Sea Hawk (novel), author, Rafael Sabatini]
  • A. Rafael Sabatini chosen
    Rafael Sabatini was an Italian-English author best known for his swashbuckling historical adventure novels such as "Scaramouche" and "Captain Blood."
  • B. Francesco Sabatini
    Francesco Sabatini was an 18th-century Italian-born architect who became a leading figure in Spanish Neoclassical architecture under King Charles III.
  • C. Valerio Bonelli
    Valerio Bonelli is a film editor known for his work on acclaimed movies such as "Philomena."
  • D. Mann Borgese
    Mann Borgese is the hyphenated family name of Elisabeth Mann Borgese, a German-born Canadian writer and influential advocate for international maritime law and ocean governance.
  • E. Conrad Marca-Relli
    Conrad Marca-Relli was an Italian-American Abstract Expressionist painter and collage artist associated with the New York School.
  • 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_69bd445edb3881909b93b34d260717fc completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7927a348819082ad531955cdf30d completed March 20, 2026, 4:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69bed933abd88190981cb16189685b8f completed March 21, 2026, 5:45 p.m.
Created at: March 20, 2026, 1:44 p.m.