Triple

T799609
Position Surface form Disambiguated ID Type / Status
Subject Macedonia (Greece) E17099 entity
Predicate containsCity P294 FINISHED
Object Edessa
Edessa is a historic city in northern Greece renowned for its picturesque waterfalls and ancient heritage.
 E105315 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: Edessa | Statement: [Macedonia (Greece), containsCity, Edessa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Edessa
Context triple: [Macedonia (Greece), containsCity, Edessa]
  • A. Edessa
    Edessa was an ancient city in Upper Mesopotamia, renowned as a major early center of Syriac Christianity and culture.
  • B. Turkmenabat
    Turkmenabat is one of the largest cities in Turkmenistan, serving as an important industrial, transport, and cultural center in the country’s east near the border with Uzbekistan.
  • C. Panticapaeum
    Panticapaeum was an important ancient Greek city and trading center on the Cimmerian Bosporus, located where the modern city of Kerch in Crimea now stands.
  • D. Tarsus
    Tarsus is an ancient city in Cilicia (in modern-day Turkey) known as a major cultural and commercial center of the Roman Empire and as the birthplace of the Apostle Paul.
  • E. Ancyra
    Ancyra is the ancient name of the city now known as Ankara, the capital of modern Turkey and a historically significant center in Anatolia.
  • 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: Edessa
Triple: [Macedonia (Greece), containsCity, Edessa]
Generated description
Edessa is a historic city in northern Greece renowned for its picturesque waterfalls and ancient heritage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Edessa
Target entity description: Edessa is a historic city in northern Greece renowned for its picturesque waterfalls and ancient heritage.
  • A. Edessa
    Edessa was an ancient city in Upper Mesopotamia, renowned as a major early center of Syriac Christianity and culture.
  • B. Turkmenabat
    Turkmenabat is one of the largest cities in Turkmenistan, serving as an important industrial, transport, and cultural center in the country’s east near the border with Uzbekistan.
  • C. Panticapaeum
    Panticapaeum was an important ancient Greek city and trading center on the Cimmerian Bosporus, located where the modern city of Kerch in Crimea now stands.
  • D. Tarsus
    Tarsus is an ancient city in Cilicia (in modern-day Turkey) known as a major cultural and commercial center of the Roman Empire and as the birthplace of the Apostle Paul.
  • E. Ancyra
    Ancyra is the ancient name of the city now known as Ankara, the capital of modern Turkey and a historically significant center in Anatolia.
  • 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_69a49378b9c48190adbf5f62e5b7aca1 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a7cb26dc8190bdd3a278b8695873 completed March 1, 2026, 8:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7c00c1db48190906a02bb80fe98dc completed March 4, 2026, 5:15 a.m.
NEDg Description generation batch_69a7c13f15848190b126bdc434953a22 completed March 4, 2026, 5:21 a.m.
NED2 Entity disambiguation (via description) batch_69a7c21dd42881908ac19fed7454d7a9 completed March 4, 2026, 5:24 a.m.
Created at: March 1, 2026, 7:38 p.m.