Triple

T8311161
Position Surface form Disambiguated ID Type / Status
Subject Isauria E194592 entity
Predicate hasCity P316 FINISHED
Object Germanicopolis
Germanicopolis was an ancient city located in the region of Isauria in Asia Minor, known from the Roman and Byzantine periods.
E726480 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: Germanicopolis | Statement: [Isauria, hasCity, Germanicopolis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Germanicopolis
Context triple: [Isauria, hasCity, Germanicopolis]
  • A. Quadratestadt
    Quadratestadt is the German nickname for the city of Mannheim, referring to its distinctive grid-like layout of city blocks.
  • B. Hemfurth
    Hemfurth is a village in central Germany best known for its proximity to the historic Eder Dam and the Edersee reservoir.
  • C. Vetus Urbs
    Vetus Urbs is the ancient core district of the Roman city of Italica, encompassing its earliest urban remains and historic center.
  • D. Metropolia
    Metropolia was the former name of the Russian Orthodox Greek Catholic Church of America, the predecessor body that evolved into today’s Orthodox Church in America.
  • E. Dorian Hexapolis
    Dorian Hexapolis was a confederation of six ancient Dorian Greek cities that formed a religious and political league centered around shared cults and festivals.
  • 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: Germanicopolis
Triple: [Isauria, hasCity, Germanicopolis]
Generated description
Germanicopolis was an ancient city located in the region of Isauria in Asia Minor, known from the Roman and Byzantine periods.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Germanicopolis
Target entity description: Germanicopolis was an ancient city located in the region of Isauria in Asia Minor, known from the Roman and Byzantine periods.
  • A. Quadratestadt
    Quadratestadt is the German nickname for the city of Mannheim, referring to its distinctive grid-like layout of city blocks.
  • B. Hemfurth
    Hemfurth is a village in central Germany best known for its proximity to the historic Eder Dam and the Edersee reservoir.
  • C. Vetus Urbs
    Vetus Urbs is the ancient core district of the Roman city of Italica, encompassing its earliest urban remains and historic center.
  • D. Metropolia
    Metropolia was the former name of the Russian Orthodox Greek Catholic Church of America, the predecessor body that evolved into today’s Orthodox Church in America.
  • E. Dorian Hexapolis
    Dorian Hexapolis was a confederation of six ancient Dorian Greek cities that formed a religious and political league centered around shared cults and festivals.
  • 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_69ca82e6e2648190a31eaf6f4f757b2a completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7f2eecb08190ae0ba8adbaf58c8f completed March 31, 2026, 8 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd956f01748190a0db22ef68126bee completed April 1, 2026, 10 p.m.
NEDg Description generation batch_69cdb20e46b881908d3c6b177e206e50 completed April 2, 2026, 12:02 a.m.
NED2 Entity disambiguation (via description) batch_69cdb654a2348190a41a6aebf96d8ea6 completed April 2, 2026, 12:20 a.m.
Created at: March 30, 2026, 5:54 p.m.