Triple

T3083454
Position Surface form Disambiguated ID Type / Status
Subject Pontus E64311 entity
Predicate containsCity P294 FINISHED
Object Trapezus
Trapezus was an ancient Greek city on the southern coast of the Black Sea, known as a key port and later as the nucleus of the medieval Empire of Trebizond.
 E325076 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: Trapezus | Statement: [Pontus, containsCity, Trapezus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Trapezus
Context triple: [Pontus, containsCity, Trapezus]
  • A. Schievelbein
    Schievelbein is a historic town in Pomerania, now known as Świdwin in northwestern Poland.
  • B. Fascian
    Fascian is a regional dialect of the Ladin language spoken in parts of northern Italy.
  • C. Caviglia
    Caviglia is an Italian surname most notably associated with the early 19th-century Egyptologist and explorer Giovanni Battista Caviglia.
  • D. Chevrier
    Chevrier is an alternative name used for the white wine grape variety Sémillon, known for producing rich, often botrytized wines, especially in Bordeaux.
  • E. Mollet
    Mollet is a French surname most notably borne by Guy Mollet, a mid-20th-century French socialist politician and former Prime Minister.
  • 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: Trapezus
Triple: [Pontus, containsCity, Trapezus]
Generated description
Trapezus was an ancient Greek city on the southern coast of the Black Sea, known as a key port and later as the nucleus of the medieval Empire of Trebizond.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Trapezus
Target entity description: Trapezus was an ancient Greek city on the southern coast of the Black Sea, known as a key port and later as the nucleus of the medieval Empire of Trebizond.
  • A. Schievelbein
    Schievelbein is a historic town in Pomerania, now known as Świdwin in northwestern Poland.
  • B. Fascian
    Fascian is a regional dialect of the Ladin language spoken in parts of northern Italy.
  • C. Caviglia
    Caviglia is an Italian surname most notably associated with the early 19th-century Egyptologist and explorer Giovanni Battista Caviglia.
  • D. Chevrier
    Chevrier is an alternative name used for the white wine grape variety Sémillon, known for producing rich, often botrytized wines, especially in Bordeaux.
  • E. Mollet
    Mollet is a French surname most notably borne by Guy Mollet, a mid-20th-century French socialist politician and former Prime Minister.
  • 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_69ad857bb4c88190a4cf27893fcabed8 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada1e877008190aacbd6f1357bdb9b completed March 8, 2026, 4:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1f89b650c8190983a00e37a42a794 completed March 11, 2026, 11:19 p.m.
NEDg Description generation batch_69b1f992a8ec8190b3e37dddd93ac57b completed March 11, 2026, 11:24 p.m.
NED2 Entity disambiguation (via description) batch_69b1f9f759408190a4f2121078fe13cb completed March 11, 2026, 11:25 p.m.
Created at: March 8, 2026, 3:03 p.m.