Triple

T23498831
Position Surface form Disambiguated ID Type / Status
Subject Roman mint E571778 entity
Predicate currency P245 FINISHED
Object Roman as
The Roman as was a bronze coin and fundamental unit of currency in ancient Rome, used widely during the Republic and early Empire before being gradually devalued and replaced.
E1588982 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: Roman as | Statement: [Roman mint, currency, Roman as]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roman as
Context triple: [Roman mint, currency, Roman as]
  • A. Romano
    Romano is an Italian masculine given name derived from the Latin word for "Roman" or "from Rome."
  • B. Romano
    Romano Mussolini was an Italian jazz pianist and painter, known both for his musical career and for being the son of dictator Benito Mussolini.
  • C. Rex Romanorum
    Rex Romanorum was the medieval title used for the elected ruler of the Holy Roman Empire, designating him as king of the Romans and future emperor.
  • D. Romitan
    Romitan is a town in Uzbekistan that serves as one of the local urban centers within the Bukhara Region.
  • E. Román
    Román is a given name and surname of Latin origin, commonly used in Spanish-speaking countries.
  • 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: Roman as
Triple: [Roman mint, currency, Roman as]
Generated description
The Roman as was a bronze coin and fundamental unit of currency in ancient Rome, used widely during the Republic and early Empire before being gradually devalued and replaced.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Roman as
Target entity description: The Roman as was a bronze coin and fundamental unit of currency in ancient Rome, used widely during the Republic and early Empire before being gradually devalued and replaced.
  • A. Romano
    Romano is an Italian masculine given name derived from the Latin word for "Roman" or "from Rome."
  • B. Romano
    Romano Mussolini was an Italian jazz pianist and painter, known both for his musical career and for being the son of dictator Benito Mussolini.
  • C. Rex Romanorum
    Rex Romanorum was the medieval title used for the elected ruler of the Holy Roman Empire, designating him as king of the Romans and future emperor.
  • D. Romitan
    Romitan is a town in Uzbekistan that serves as one of the local urban centers within the Bukhara Region.
  • E. Román
    Román is a given name and surname of Latin origin, commonly used in Spanish-speaking countries.
  • 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_69e245b4829881909b77a70e942bbd54 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a7e184ec8190aff3677c9b00a8f2 completed April 29, 2026, 6:40 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c827401888190bc01ad0a02238698 completed May 19, 2026, 3:32 p.m.
NEDg Description generation batch_6a0ca6f229308190bf72b52fd44144d3 completed May 19, 2026, 6:07 p.m.
NED2 Entity disambiguation (via description) batch_6a0ca7f09af48190b7bfdae25d2f286b completed May 19, 2026, 6:12 p.m.
Created at: April 17, 2026, 6:06 p.m.