Triple

T16287880
Position Surface form Disambiguated ID Type / Status
Subject Ceos E395436 entity
Predicate hasAncientCity P17588 FINISHED
Object Koressia
Koressia was an ancient city on the Aegean island of Ceos (Keos), known from classical Greek history and archaeology.
E1203988 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: Koressia | Statement: [Ceos, hasAncientCity, Koressia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Koressia
Context triple: [Ceos, hasAncientCity, Koressia]
  • A. Kusaila
    Kusaila was a 7th-century Berber Christian leader and military commander who led resistance against the early Muslim expansion in North Africa.
  • B. Kissamos
    Kissamos is a coastal town and municipality on the western part of the Greek island of Crete, known for its nearby beaches and archaeological sites.
  • C. Nekede
    Nekede is a suburban community in Imo State, Nigeria, known for hosting the Federal Polytechnic Nekede and lying on the outskirts of the city of Owerri.
  • D. Kochari
    Kochari is a traditional Armenian circle dance characterized by energetic steps, rhythmic stomping, and strong communal participation at celebrations and cultural events.
  • E. Unioninkatu
    Unioninkatu is a central street in Helsinki, Finland, known for running through the historic city center and hosting key institutions such as the University of Helsinki.
  • 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: Koressia
Triple: [Ceos, hasAncientCity, Koressia]
Generated description
Koressia was an ancient city on the Aegean island of Ceos (Keos), known from classical Greek history and archaeology.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Koressia
Target entity description: Koressia was an ancient city on the Aegean island of Ceos (Keos), known from classical Greek history and archaeology.
  • A. Kusaila
    Kusaila was a 7th-century Berber Christian leader and military commander who led resistance against the early Muslim expansion in North Africa.
  • B. Kissamos
    Kissamos is a coastal town and municipality on the western part of the Greek island of Crete, known for its nearby beaches and archaeological sites.
  • C. Nekede
    Nekede is a suburban community in Imo State, Nigeria, known for hosting the Federal Polytechnic Nekede and lying on the outskirts of the city of Owerri.
  • D. Kochari
    Kochari is a traditional Armenian circle dance characterized by energetic steps, rhythmic stomping, and strong communal participation at celebrations and cultural events.
  • E. Unioninkatu
    Unioninkatu is a central street in Helsinki, Finland, known for running through the historic city center and hosting key institutions such as the University of Helsinki.
  • 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_69d87f22c7248190a54c949738441e2e completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e24915a5948190a11b8e83b7974dda completed April 17, 2026, 2:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0017caaa448190a5034ddbd90d2fd5 completed May 10, 2026, 5:29 a.m.
NEDg Description generation batch_6a0018951f888190b70e098e4af3a90a completed May 10, 2026, 5:33 a.m.
NED2 Entity disambiguation (via description) batch_6a00190887088190a5a0eb2cfd674c98 completed May 10, 2026, 5:35 a.m.
Created at: April 10, 2026, 5:05 a.m.