Triple

T2113269
Position Surface form Disambiguated ID Type / Status
Subject Siege of Segusio E42550 entity
Predicate location P40 FINISHED
Object Segusio
Segusio was an ancient Roman town in the Alps, strategically located on key transalpine routes in what is now Susa, Italy.
E235215 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: Segusio | Statement: [Siege of Segusio, location, Segusio]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Segusio
Context triple: [Siege of Segusio, location, Segusio]
  • A. Sicel
    Sicel was an ancient Indo-European language once spoken by the Sicel people in eastern Sicily before the dominance of Latin and Greek in the region.
  • B. Sabinum
    Sabinum was the ancient central Italian region traditionally associated with the Sabine people, located in the Apennine area northeast of Rome.
  • C. Caprile
    Caprile is a surname associated with the architectural firm Lohan Caprile Goettsch Architects.
  • D. Caesonia
    Caesonia is a Roman cognomen (family name) used by women of the gens Atia in ancient Rome.
  • E. Gattilusio
    Gattilusio is the surname of a prominent Genoese noble family that ruled several Aegean islands and territories in the late medieval period.
  • 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: Segusio
Triple: [Siege of Segusio, location, Segusio]
Generated description
Segusio was an ancient Roman town in the Alps, strategically located on key transalpine routes in what is now Susa, Italy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Segusio
Target entity description: Segusio was an ancient Roman town in the Alps, strategically located on key transalpine routes in what is now Susa, Italy.
  • A. Sicel
    Sicel was an ancient Indo-European language once spoken by the Sicel people in eastern Sicily before the dominance of Latin and Greek in the region.
  • B. Sabinum
    Sabinum was the ancient central Italian region traditionally associated with the Sabine people, located in the Apennine area northeast of Rome.
  • C. Caprile
    Caprile is a surname associated with the architectural firm Lohan Caprile Goettsch Architects.
  • D. Caesonia
    Caesonia is a Roman cognomen (family name) used by women of the gens Atia in ancient Rome.
  • E. Gattilusio
    Gattilusio is the surname of a prominent Genoese noble family that ruled several Aegean islands and territories in the late medieval period.
  • 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_69a8871040f08190aac2e2d0ab6b47ad completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abbb0495d0819097dc936540743b74 completed March 7, 2026, 5:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae30748a7c81908ab3e08b7aa9900a completed March 9, 2026, 2:29 a.m.
NEDg Description generation batch_69ae3197794c81908530b26fcb8a4a77 completed March 9, 2026, 2:33 a.m.
NED2 Entity disambiguation (via description) batch_69ae31f65444819090c2af22c21ec3e1 completed March 9, 2026, 2:35 a.m.
Created at: March 4, 2026, 7:43 p.m.