Triple

T9713880
Position Surface form Disambiguated ID Type / Status
Subject Ezana of Aksum E235089 entity
Predicate succeededBy P78 FINISHED
Object MHDYS
MHDYS was a king of the ancient Kingdom of Aksum, known from inscriptions and coins as a later Aksumite ruler active during the 4th–5th centuries CE.
 E817015 NE FINISHED

How this triple was built (4 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: MHDYS | Statement: [Ezana of Aksum, succeededBy, MHDYS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MHDYS
Context triple: [Ezana of Aksum, succeededBy, MHDYS]
  • A. MHD
    MHD is a French rapper known for pioneering the Afro trap genre, blending hip-hop with African musical influences.
  • B. HdM
    HdM is the commonly used abbreviation for Stuttgart Media University, a German university specializing in media, information, and communication studies.
  • C. MDH
    MDH is the commonly used abbreviation for the Faculty of Medicine, Dentistry and Health, an academic division focused on education and research in medical, dental and health sciences.
  • D. MDH
    MDH is the acronym for the Maryland Department of Health, the state agency responsible for public health services, policy, and regulation in Maryland.
  • E. MCDHH
    MCDHH is the state agency in Massachusetts responsible for providing services, advocacy, and resources for deaf and hard of hearing individuals.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: MHDYS
Triple: [Ezana of Aksum, succeededBy, MHDYS]
Generated description
MHDYS was a king of the ancient Kingdom of Aksum, known from inscriptions and coins as a later Aksumite ruler active during the 4th–5th centuries CE.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MHDYS
Target entity description: MHDYS was a king of the ancient Kingdom of Aksum, known from inscriptions and coins as a later Aksumite ruler active during the 4th–5th centuries CE.
  • A. MHD
    MHD is a French rapper known for pioneering the Afro trap genre, blending hip-hop with African musical influences.
  • B. HdM
    HdM is the commonly used abbreviation for Stuttgart Media University, a German university specializing in media, information, and communication studies.
  • C. MDH
    MDH is the commonly used abbreviation for the Faculty of Medicine, Dentistry and Health, an academic division focused on education and research in medical, dental and health sciences.
  • D. MDH
    MDH is the acronym for the Maryland Department of Health, the state agency responsible for public health services, policy, and regulation in Maryland.
  • E. MCDHH
    MCDHH is the state agency in Massachusetts responsible for providing services, advocacy, and resources for deaf and hard of hearing individuals.
  • F. None of above. chosen

Provenance (5 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_69ca84cd8fa0819090a5e243ceb37003 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9e087a1c8190aa62c910f88e8516 completed April 1, 2026, 10:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19f900ca08190a52f042feab2afa3 completed April 4, 2026, 11:32 p.m.
NEDg Description generation batch_69d1a181f10081908bfb0fae5a08462f completed April 4, 2026, 11:40 p.m.
NED2 Entity disambiguation (via description) batch_69d1a228b8488190a5a61f3468e92649 completed April 4, 2026, 11:43 p.m.
Created at: March 30, 2026, 8:19 p.m.