Triple

T18272720
Position Surface form Disambiguated ID Type / Status
Subject Rasis E437653 entity
Predicate influenced P9 FINISHED
Object Ibn Sina 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: Ibn Sina | Statement: [Rasis, influenced, Ibn Sina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ibn Sina
Context triple: [Rasis, influenced, Ibn Sina]
  • A. Avicenna chosen
    Avicenna was an influential Persian polymath and philosopher of the Islamic Golden Age, best known for his works in metaphysics and medicine, especially "The Book of Healing" and "The Canon of Medicine."
  • B. Al-Razi (Rhazes)
    Al-Razi (Rhazes) was a pioneering Persian polymath and physician renowned for his influential works in medicine, chemistry, and philosophy during the early Islamic world.
  • C. Abu al-Qasim
    Abu al-Qasim is the honorific kunya of Muhammad ibn al-Hanafiyyah, a prominent early Islamic figure and son of Ali ibn Abi Talib.
  • D. Abu Rayhan
    Abu Rayhan was the honorific name of Al-Biruni, a renowned 11th-century Persian polymath known for his influential works in astronomy, mathematics, geography, and comparative religion.
  • E. Abul-Qasim
    Abul-Qasim is the honorific given name of the Persian poet Ferdowsi, famed author of the epic Shahnameh.
  • 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_69d8b914530c8190b4474d862a2b2a1b completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e5004f0e7c8190a7206e193012a2d3 completed April 19, 2026, 4:18 p.m.
Created at: April 10, 2026, 10:34 a.m.