Triple

T10274563
Position Surface form Disambiguated ID Type / Status
Subject Idris II E240928 entity
Predicate predecessor P97 FINISHED
Object Idris I E397680 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: Idris I | Statement: [Idris II, predecessor, Idris I]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Idris I
Context triple: [Idris II, predecessor, Idris I]
  • A. Idris I chosen
    Idris I was an 8th-century Arab leader and descendant of the Prophet Muhammad who established one of the earliest Islamic states in Morocco, laying the foundations of the Idrisid dynasty.
  • B. Idris II
    Idris II was an early 9th-century Idrisid ruler of Morocco who consolidated Islamic rule in the region and is traditionally credited with making Fez a major political and religious center.
  • C. Idris
    Idris is the central protagonist of Mary Shelley’s apocalyptic novel "The Last Man," navigating a world devastated by plague and societal collapse.
  • D. Idris
    Idris is an ancient prophet in Islamic tradition, often identified with the biblical Enoch and revered for his wisdom, piety, and early mastery of writing and knowledge.
  • E. Idris
    Idris is a functional programming language with full dependent types, designed for expressive type-driven development and interactive theorem proving.
  • 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_69d381a94c1881908fc38fc263d9b9c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d28a9c508190824867c04e8dcbe7 completed April 7, 2026, 9:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69d75001586c8190a0d4af1ff5588f0e completed April 9, 2026, 7:06 a.m.
Created at: April 6, 2026, 11:36 a.m.