Triple

T10547696
Position Surface form Disambiguated ID Type / Status
Subject Arghun E248864 entity
Predicate predecessor P97 FINISHED
Object Tekuder E242160 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: Tekuder | Statement: [Arghun, predecessor, Tekuder]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tekuder
Context triple: [Arghun, predecessor, Tekuder]
  • A. Tekuder chosen
    Tekuder was a 13th-century Ilkhanid ruler of the Mongol Empire in Persia who converted to Islam and briefly reigned amid intense dynastic and religious conflicts.
  • B. Fetha Nagast
    Fetha Nagast is a historic Ethiopian legal code written in Ge'ez that served for centuries as a foundational source of both civil and ecclesiastical law in Ethiopia.
  • C. Debre Markos
    Debre Markos is a prominent historic town and administrative center in northwestern Ethiopia’s Amhara region, known for its religious heritage and role as a regional hub.
  • D. Tachenwit
    Tachenwit is an alternative name for the Chenoua language, a Berber language spoken in northern Algeria.
  • E. Tullu Dimtu
    Tullu Dimtu is the highest peak in Ethiopia’s Bale Mountains, known for its alpine landscapes and unique Afro-alpine biodiversity.
  • 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_69d381c733c08190ab1dd6239f5f34ae completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d526d20ef48190ab9f70d4ce5f2a11 completed April 7, 2026, 3:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69d94b3148dc81908720c27e58a325ab completed April 10, 2026, 7:10 p.m.
Created at: April 6, 2026, 12:33 p.m.