Triple

T2813619
Position Surface form Disambiguated ID Type / Status
Subject Persian Letters E54230 entity
Predicate hasCharacter P2308 FINISHED
Object Roxane E52073 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: Roxane | Statement: [Persian Letters, hasCharacter, Roxane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roxane
Context triple: [Persian Letters, hasCharacter, Roxane]
  • A. Roxane chosen
    Roxane is a feminine given name, best known today through figures such as writer and cultural critic Roxane Gay.
  • B. Roxane
    Roxane is a historical figure traditionally identified as a daughter of Cyrus the Great, the founder of the Achaemenid Persian Empire.
  • C. Roxana
    Roxana is a feminine given name of Persian origin, historically associated with figures such as the wife of Alexander the Great and later borne by various notable women.
  • D. Leonora
    Leonora is a feminine given name used in various cultures, often considered a variant of Eleanor or Leonore.
  • E. Troilus
    Troilus is a young Trojan prince from Greek mythology, often associated with tragic love and prophecy in the legends surrounding the Trojan War.
  • 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_69ab49de0af08190b3da69683be1e728 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abde4ba34c819085a336498fc326b0 completed March 7, 2026, 8:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69afce9cd4ec81908900ffee0edb70ca completed March 10, 2026, 7:56 a.m.
Created at: March 6, 2026, 9:59 p.m.