Triple

T782083
Position Surface form Disambiguated ID Type / Status
Subject Epirus E16518 entity
Predicate hasArchaeologicalSite P1098 FINISHED
Object Nikopolis
Nikopolis is an ancient city in Epirus, Greece, founded by the Roman emperor Augustus and known today for its extensive archaeological remains.
E107375 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: Nikopolis | Statement: [Epirus, hasArchaeologicalSite, Nikopolis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nikopolis
Context triple: [Epirus, hasArchaeologicalSite, Nikopolis]
  • A. Naissus
    Naissus was an important ancient Roman city in the province of Moesia, located at the site of modern-day Niš in Serbia.
  • B. Pherae
    Pherae was an ancient Greek city in Thessaly known for its political influence and as the seat of the powerful tyrant Jason of Pherae.
  • C. Lampsacus
    Lampsacus was an ancient Greek city on the eastern shore of the Hellespont, known as a center of philosophy and culture in classical antiquity.
  • D. 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.
  • E. Pella
    Pella is a well-known American brand specializing in the design and manufacture of windows and doors for residential and commercial buildings.
  • 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: Nikopolis
Triple: [Epirus, hasArchaeologicalSite, Nikopolis]
Generated description
Nikopolis is an ancient city in Epirus, Greece, founded by the Roman emperor Augustus and known today for its extensive archaeological remains.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Nikopolis
Target entity description: Nikopolis is an ancient city in Epirus, Greece, founded by the Roman emperor Augustus and known today for its extensive archaeological remains.
  • A. Naissus
    Naissus was an important ancient Roman city in the province of Moesia, located at the site of modern-day Niš in Serbia.
  • B. Pherae
    Pherae was an ancient Greek city in Thessaly known for its political influence and as the seat of the powerful tyrant Jason of Pherae.
  • C. Lampsacus
    Lampsacus was an ancient Greek city on the eastern shore of the Hellespont, known as a center of philosophy and culture in classical antiquity.
  • D. 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.
  • E. Pella
    Pella is a well-known American brand specializing in the design and manufacture of windows and doors for residential and commercial buildings.
  • 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_69a4936ad1fc81908f190208059ccf78 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a765ba688190ab328bb159583077 completed March 1, 2026, 8:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7c70e6eb48190b019759cd656e629 completed March 4, 2026, 5:45 a.m.
NEDg Description generation batch_69a7c896d1c481909493a1bc4e6266e3 completed March 4, 2026, 5:52 a.m.
NED2 Entity disambiguation (via description) batch_69a7c918ebbc81908ad58bb8045543e6 completed March 4, 2026, 5:54 a.m.
Created at: March 1, 2026, 7:37 p.m.