Triple

T2889057
Position Surface form Disambiguated ID Type / Status
Subject Michael I Cerularius E59576 entity
Predicate deathPlace P21 FINISHED
Object Madytos
Madytos was a town in the Byzantine Empire, located in the region of the Hellespont in what is now northwestern Turkey.
 E308560 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: Madytos | Statement: [Michael I Cerularius, deathPlace, Madytos]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Madytos
Context triple: [Michael I Cerularius, deathPlace, Madytos]
  • A. Mže
    Mže is a river in the Czech Republic that flows through the city of Plzeň and forms part of the Berounka river system.
  • B. Naisos
    Naisos is an alternative name for Naissus, the ancient city located at the site of modern-day Niš in Serbia, historically significant as a major Roman and Byzantine center.
  • C. Myaso
    Myaso is a colloquial nickname used by fans and rivals to refer to the Russian football club Spartak Moscow, reflecting its historical association with the meat industry.
  • D. Nuska
    Nuska is a Mesopotamian god of fire and light, often serving as a divine vizier and attendant to major deities in the Sumerian and Akkadian pantheons.
  • E. Mykelti
    Mykelti is the distinctive given name of American actor Mykelti Williamson, known for roles in films like "Forrest Gump" and various television series.
  • 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: Madytos
Triple: [Michael I Cerularius, deathPlace, Madytos]
Generated description
Madytos was a town in the Byzantine Empire, located in the region of the Hellespont in what is now northwestern Turkey.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Madytos
Target entity description: Madytos was a town in the Byzantine Empire, located in the region of the Hellespont in what is now northwestern Turkey.
  • A. Mže
    Mže is a river in the Czech Republic that flows through the city of Plzeň and forms part of the Berounka river system.
  • B. Naisos
    Naisos is an alternative name for Naissus, the ancient city located at the site of modern-day Niš in Serbia, historically significant as a major Roman and Byzantine center.
  • C. Myaso
    Myaso is a colloquial nickname used by fans and rivals to refer to the Russian football club Spartak Moscow, reflecting its historical association with the meat industry.
  • D. Nuska
    Nuska is a Mesopotamian god of fire and light, often serving as a divine vizier and attendant to major deities in the Sumerian and Akkadian pantheons.
  • E. Mykelti
    Mykelti is the distinctive given name of American actor Mykelti Williamson, known for roles in films like "Forrest Gump" and various television series.
  • 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_69ab4ac739188190a112f42a5a69c951 completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abe04918908190aad08defd1b26d97 completed March 7, 2026, 8:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69b03179d7448190bcdbea164856aaa2 completed March 10, 2026, 2:58 p.m.
NEDg Description generation batch_69b03f0c5bac81909aa21d5963a86c92 completed March 10, 2026, 3:55 p.m.
NED2 Entity disambiguation (via description) batch_69b044c1ea3c8190a9ae7c1431d3a3f2 completed March 10, 2026, 4:20 p.m.
Created at: March 6, 2026, 10:04 p.m.