Triple

T1453733
Position Surface form Disambiguated ID Type / Status
Subject Byzantium E31350 entity
Predicate namedAfter P63 FINISHED
Object Byzas
Byzas is the legendary Greek founder of the ancient city of Byzantium, later known as Constantinople and Istanbul.
 E175452 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: Byzas | Statement: [Byzantium, namedAfter, Byzas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Byzas
Context triple: [Byzantium, namedAfter, Byzas]
  • A. Byzantium
    Byzantium was an ancient Greek city on the Bosporus that later became the Roman and Byzantine imperial capital of Constantinople, now Istanbul.
  • B. İznik
    İznik is a historic town in northwestern Turkey, renowned as the site of the First Council of Nicaea and for its rich Byzantine and Ottoman heritage.
  • C. Naissus
    Naissus was an important ancient Roman city in the province of Moesia, located at the site of modern-day Niš in Serbia.
  • D. Diospolis
    Diospolis is the ancient name of the city historically known as Lydda (modern Lod) in central Israel, an important urban center in classical and early Christian periods.
  • E. Nicomedia (traditionally)
    Nicomedia (traditionally) is an ancient city in northwestern Asia Minor, near the Sea of Marmara, that served as a major Roman and later Byzantine administrative center.
  • 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: Byzas
Triple: [Byzantium, namedAfter, Byzas]
Generated description
Byzas is the legendary Greek founder of the ancient city of Byzantium, later known as Constantinople and Istanbul.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Byzas
Target entity description: Byzas is the legendary Greek founder of the ancient city of Byzantium, later known as Constantinople and Istanbul.
  • A. Byzantium
    Byzantium was an ancient Greek city on the Bosporus that later became the Roman and Byzantine imperial capital of Constantinople, now Istanbul.
  • B. İznik
    İznik is a historic town in northwestern Turkey, renowned as the site of the First Council of Nicaea and for its rich Byzantine and Ottoman heritage.
  • C. Naissus
    Naissus was an important ancient Roman city in the province of Moesia, located at the site of modern-day Niš in Serbia.
  • D. Diospolis
    Diospolis is the ancient name of the city historically known as Lydda (modern Lod) in central Israel, an important urban center in classical and early Christian periods.
  • E. Nicomedia (traditionally)
    Nicomedia (traditionally) is an ancient city in northwestern Asia Minor, near the Sea of Marmara, that served as a major Roman and later Byzantine administrative center.
  • 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_69a499171a28819085b993a3ac78e363 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c57e82d48190a30a4512f39f5de0 completed March 1, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad30877a348190a99dbeaf45cd0335 completed March 8, 2026, 8:17 a.m.
NEDg Description generation batch_69ad312e77ac8190b931a42317f2cefa completed March 8, 2026, 8:19 a.m.
NED2 Entity disambiguation (via description) batch_69ad3184853c8190953b288693ce6ea4 completed March 8, 2026, 8:21 a.m.
Created at: March 1, 2026, 8 p.m.