Triple

T20961661
Position Surface form Disambiguated ID Type / Status
Subject Musa al-Kadhim E516262 entity
Predicate patronymic P7966 FINISHED
Object ibn Jaʿfar E688849 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: ibn Jaʿfar | Statement: [Musa al-Kadhim, patronymic, ibn Jaʿfar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ibn Jaʿfar
Context triple: [Musa al-Kadhim, patronymic, ibn Jaʿfar]
  • A. ibn Jaʿfar chosen
    ibn Jaʿfar is a patronymic referring to a descendant or son of Jaʿfar, notably used for the seventh Shia Imam, Musa al-Kadhim.
  • B. ibn Zakariya
    Ibn Zakariya refers to Abu Bakr Muhammad ibn Zakariya al-Razi, a renowned 9th–10th century Persian polymath celebrated for his influential works in medicine, alchemy, and philosophy.
  • C. ibn Ali
    Ibn Ali is a patronymic name indicating a person as the son of someone named Ali, here referring specifically to the lineage of the Persian vizier Nizam al-Mulk.
  • D. ibn Jahsh
    Ibn Jahsh is a patronymic referring to members of an early 7th-century Arabian family that included several companions and relatives of the Prophet Muhammad.
  • E. ibn Idris
    Ibn Idris is the patronymic of the influential early Islamic jurist and theologian Al-Shafi'i, founder of the Shafi'i school of Sunni law.
  • 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_69e0b4fde6c48190af1398e7e734629e completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fb6fd1d48190ad0ec7eb72f84889 completed April 21, 2026, 4:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a092798800481909d437b58467f8e2b completed May 17, 2026, 2:27 a.m.
Created at: April 16, 2026, 1:31 p.m.