Triple

T2684290
Position Surface form Disambiguated ID Type / Status
Subject Le Puy-en-Velay E57445 entity
Predicate formerName P65 FINISHED
Object Anicium
Anicium is the historical Latin name of the French town now known as Le Puy-en-Velay.
 E287496 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: Anicium | Statement: [Le Puy-en-Velay, formerName, Anicium]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Anicium
Context triple: [Le Puy-en-Velay, formerName, Anicium]
  • A. Sabinum
    Sabinum was the ancient central Italian region traditionally associated with the Sabine people, located in the Apennine area northeast of Rome.
  • B. Lavinium
    Lavinium was an ancient coastal city of Latium in central Italy, traditionally associated with the legendary landing of Aeneas and the early origins of Roman religious cults.
  • C. Saepinum
    Saepinum was an ancient town of the Samnite people in south-central Italy, later developed into a Roman municipium whose ruins are still visible today.
  • D. Marrucini
    The Marrucini were an ancient Italic tribe of central Italy, closely associated with neighboring peoples like the Marsi and Paeligni and later incorporated into the Roman state.
  • E. Arpinum
    Arpinum is an ancient Italian town in Latium best known as the birthplace of the Roman statesman and orator Cicero.
  • 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: Anicium
Triple: [Le Puy-en-Velay, formerName, Anicium]
Generated description
Anicium is the historical Latin name of the French town now known as Le Puy-en-Velay.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Anicium
Target entity description: Anicium is the historical Latin name of the French town now known as Le Puy-en-Velay.
  • A. Sabinum
    Sabinum was the ancient central Italian region traditionally associated with the Sabine people, located in the Apennine area northeast of Rome.
  • B. Lavinium
    Lavinium was an ancient coastal city of Latium in central Italy, traditionally associated with the legendary landing of Aeneas and the early origins of Roman religious cults.
  • C. Saepinum
    Saepinum was an ancient town of the Samnite people in south-central Italy, later developed into a Roman municipium whose ruins are still visible today.
  • D. Marrucini
    The Marrucini were an ancient Italic tribe of central Italy, closely associated with neighboring peoples like the Marsi and Paeligni and later incorporated into the Roman state.
  • E. Arpinum
    Arpinum is an ancient Italian town in Latium best known as the birthplace of the Roman statesman and orator Cicero.
  • 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_69ab4a5028388190a36f3baf1588309e completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd9d7692c81909d8fd9ce3817161b completed March 7, 2026, 7:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69afa0700d548190944544495a2d42f6 completed March 10, 2026, 4:39 a.m.
NEDg Description generation batch_69afa1196aac81909b25557dff5acf5e completed March 10, 2026, 4:42 a.m.
NED2 Entity disambiguation (via description) batch_69afa1a7d9b48190a8b14a7d209e1f26 completed March 10, 2026, 4:44 a.m.
Created at: March 6, 2026, 9:54 p.m.