Triple

T21159966
Position Surface form Disambiguated ID Type / Status
Subject Two Arabian Knights E521412 entity
Predicate hasCharacter P2308 FINISHED
Object Mirza 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: Mirza | Statement: [Two Arabian Knights, hasCharacter, Mirza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mirza
Context triple: [Two Arabian Knights, hasCharacter, Mirza]
  • A. Mirza chosen
    Mirza is a historical noble title of Persian and Central Asian origin, commonly borne by princes and high-ranking members of royal and aristocratic families.
  • B. Murtaza
    Murtaza is a well-known Turkish novel by Orhan Kemal that portrays the struggles and mentality of an overzealous night watchman in a changing society.
  • C. Shahzada
    Shahzada is a royal title used in Persianate and South Asian cultures to denote a prince or son of a monarch.
  • D. Mirza Khazar
    Mirza Khazar is a prominent Azerbaijani-American journalist, translator, and broadcaster best known for his influential work with Radio Free Europe/Radio Liberty and his modern Azerbaijani translation of the Bible.
  • E. Zahir
    Zahir is a given name of Arabic origin meaning "shining," "radiant," or "evident," used across various cultures as a masculine first or middle name.
  • 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_69e0b50d1ea481909c07e63c3ead9316 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7252f70888190b8e6109cc4099ecc completed April 21, 2026, 7:20 a.m.
Created at: April 16, 2026, 2:59 p.m.