Triple

T2101178
Position Surface form Disambiguated ID Type / Status
Subject Via Aurelia E37095 entity
Predicate passedThrough P3448 FINISHED
Object Cosa
Cosa is an ancient Etruscan and later Roman coastal town in Tuscany, Italy, known for its archaeological remains overlooking the Tyrrhenian Sea.
E233955 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: Cosa | Statement: [Via Aurelia, passedThrough, Cosa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cosa
Context triple: [Via Aurelia, passedThrough, Cosa]
  • A. Essa
    Essa is a rural township in Simcoe County, Ontario, Canada, known for its agricultural landscape and proximity to the city of Barrie.
  • B. Nesta
    Nesta is the middle name of legendary Jamaican reggae musician and cultural icon Bob Marley.
  • C. Cáqueza
    Cáqueza is a small municipality and town in the Andean region of central Colombia, known for its rural landscapes and proximity to Bogotá in the department of Cundinamarca.
  • D. Cassibile
    Cassibile is a village in southeastern Sicily, Italy, historically notable as the site where the 1943 armistice between Italy and the Allies was signed during World War II.
  • E. Crisa
    Crisa was an ancient Greek town near Delphi that played a central role in the First Sacred War over control of the sanctuary and its access routes.
  • 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: Cosa
Triple: [Via Aurelia, passedThrough, Cosa]
Generated description
Cosa is an ancient Etruscan and later Roman coastal town in Tuscany, Italy, known for its archaeological remains overlooking the Tyrrhenian Sea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Cosa
Target entity description: Cosa is an ancient Etruscan and later Roman coastal town in Tuscany, Italy, known for its archaeological remains overlooking the Tyrrhenian Sea.
  • A. Essa
    Essa is a rural township in Simcoe County, Ontario, Canada, known for its agricultural landscape and proximity to the city of Barrie.
  • B. Nesta
    Nesta is the middle name of legendary Jamaican reggae musician and cultural icon Bob Marley.
  • C. Cáqueza
    Cáqueza is a small municipality and town in the Andean region of central Colombia, known for its rural landscapes and proximity to Bogotá in the department of Cundinamarca.
  • D. Cassibile
    Cassibile is a village in southeastern Sicily, Italy, historically notable as the site where the 1943 armistice between Italy and the Allies was signed during World War II.
  • E. Crisa
    Crisa was an ancient Greek town near Delphi that played a central role in the First Sacred War over control of the sanctuary and its access routes.
  • 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_69a8861828948190924aa30c08806b3a completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abbabb512c819087b1d5ec8ef11e63 completed March 7, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae3065f3588190bc483e07dda8cf71 completed March 9, 2026, 2:28 a.m.
NEDg Description generation batch_69ae3106488c8190a044d843a10f531a completed March 9, 2026, 2:31 a.m.
NED2 Entity disambiguation (via description) batch_69ae31889bc0819092810ade1961d10e completed March 9, 2026, 2:33 a.m.
Created at: March 4, 2026, 7:43 p.m.