Triple

T1492763
Position Surface form Disambiguated ID Type / Status
Subject Ibrahim ibn Muhammad E29617 entity
Predicate relative P37 FINISHED
Object Qasim ibn Muhammad E28927 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: Qasim ibn Muhammad | Statement: [Ibrahim ibn Muhammad, relative, Qasim ibn Muhammad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Qasim ibn Muhammad
Context triple: [Ibrahim ibn Muhammad, relative, Qasim ibn Muhammad]
  • A. Qasim ibn Muhammad chosen
    Qasim ibn Muhammad was the eldest son of the Islamic prophet Muhammad, who died in childhood in Mecca.
  • B. Al-Qasim ibn Muhammad ibn Abi Bakr
    Al-Qasim ibn Muhammad ibn Abi Bakr was a prominent early Islamic jurist and one of the renowned Seven Fuqaha of Medina, known for his deep scholarship in hadith and law.
  • C. Muhammad al-Shaybani
    Muhammad al-Shaybani was an influential early Islamic jurist and student of Abu Hanifa who played a key role in systematizing and transmitting Hanafi jurisprudence.
  • D. Abdullah ibn Muhammad
    Abdullah ibn Muhammad was one of the sons of the Islamic prophet Muhammad who died in early childhood.
  • E. Umara ibn Hamza
    Umara ibn Hamza was an early Islamic figure known primarily as a descendant of the Prophet Muhammad’s uncle Hamza ibn Abd al-Muttalib.
  • 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_69a498dba1d8819093b46a3a8d2485f1 completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c6c4f0c88190a97ba4910c1a5d85 completed March 1, 2026, 11:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69ae303a4f5881909746b1dae558f8b0 completed March 9, 2026, 2:28 a.m.
Created at: March 1, 2026, 8:12 p.m.