Triple

T901937
Position Surface form Disambiguated ID Type / Status
Subject Edirne E19465 entity
Predicate formerName P65 FINISHED
Object Hadrianopolis
Hadrianopolis was an important ancient Roman and Byzantine city in Thrace, later known as Edirne in modern-day Turkey.
 E110819 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: Hadrianopolis | Statement: [Edirne, formerName, Hadrianopolis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hadrianopolis
Context triple: [Edirne, formerName, Hadrianopolis]
  • A. Nikopolis
    Nikopolis is an ancient city in Epirus, Greece, founded by the Roman emperor Augustus and known today for its extensive archaeological remains.
  • B. Naissus
    Naissus was an important ancient Roman city in the province of Moesia, located at the site of modern-day Niš in Serbia.
  • C. Sirmium
    Sirmium was an important ancient Roman city in the province of Pannonia, serving as a major military, administrative, and imperial center in the late Roman Empire.
  • D. Edessa
    Edessa is a historic city in northern Greece renowned for its picturesque waterfalls and ancient heritage.
  • E. Edessa
    Edessa was an ancient city in Upper Mesopotamia, renowned as a major early center of Syriac Christianity and culture.
  • 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: Hadrianopolis
Triple: [Edirne, formerName, Hadrianopolis]
Generated description
Hadrianopolis was an important ancient Roman and Byzantine city in Thrace, later known as Edirne in modern-day Turkey.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hadrianopolis
Target entity description: Hadrianopolis was an important ancient Roman and Byzantine city in Thrace, later known as Edirne in modern-day Turkey.
  • A. Nikopolis
    Nikopolis is an ancient city in Epirus, Greece, founded by the Roman emperor Augustus and known today for its extensive archaeological remains.
  • B. Naissus
    Naissus was an important ancient Roman city in the province of Moesia, located at the site of modern-day Niš in Serbia.
  • C. Sirmium
    Sirmium was an important ancient Roman city in the province of Pannonia, serving as a major military, administrative, and imperial center in the late Roman Empire.
  • D. Edessa
    Edessa is a historic city in northern Greece renowned for its picturesque waterfalls and ancient heritage.
  • E. Edessa
    Edessa was an ancient city in Upper Mesopotamia, renowned as a major early center of Syriac Christianity and culture.
  • 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_69a4939e889c8190ac148b3ac1a7f90b completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ad4412408190a6bf8fc7484a5781 completed March 1, 2026, 9:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69a826d6781081908a59c0263515bbc8 completed March 4, 2026, 12:34 p.m.
NEDg Description generation batch_69a834246eec8190977b2d3747fa1e9d completed March 4, 2026, 1:31 p.m.
NED2 Entity disambiguation (via description) batch_69a834a0e6748190aa1c488a46f35df2 completed March 4, 2026, 1:33 p.m.
Created at: March 1, 2026, 7:39 p.m.