Triple

T11607389
Position Surface form Disambiguated ID Type / Status
Subject T-68 tram E275296 entity
Predicate manufacturer P490 FINISHED
Object Firema
Firema is an Italian rolling stock manufacturer known for producing trams, trains, and other railway vehicles.
 E936445 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: Firema | Statement: [T-68 tram, manufacturer, Firema]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Firema
Context triple: [T-68 tram, manufacturer, Firema]
  • A. Firmum
    Firmum was an important ancient town in Picenum, a region of central Italy along the Adriatic coast in the Roman era.
  • B. Fumusa
    Fumusa is an Italian-origin surname most notably associated with American actor Dominic Fumusa.
  • C. Fannrem
    Fannrem is a village in Trøndelag county, Norway, known as one of the main settlements within the municipality of Orkland.
  • D. Fideuram
    Fideuram is a prominent Italian private banking and wealth management institution operating within the Intesa Sanpaolo banking group.
  • E. Fainall
    Fainall is a central, scheming antagonist in William Congreve’s Restoration comedy "The Way of the World," known for his manipulative and duplicitous nature.
  • 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: Firema
Triple: [T-68 tram, manufacturer, Firema]
Generated description
Firema is an Italian rolling stock manufacturer known for producing trams, trains, and other railway vehicles.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Firema
Target entity description: Firema is an Italian rolling stock manufacturer known for producing trams, trains, and other railway vehicles.
  • A. Firmum
    Firmum was an important ancient town in Picenum, a region of central Italy along the Adriatic coast in the Roman era.
  • B. Fumusa
    Fumusa is an Italian-origin surname most notably associated with American actor Dominic Fumusa.
  • C. Fannrem
    Fannrem is a village in Trøndelag county, Norway, known as one of the main settlements within the municipality of Orkland.
  • D. Fideuram
    Fideuram is a prominent Italian private banking and wealth management institution operating within the Intesa Sanpaolo banking group.
  • E. Fainall
    Fainall is a central, scheming antagonist in William Congreve’s Restoration comedy "The Way of the World," known for his manipulative and duplicitous nature.
  • 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_69d6aaf84b548190ac072e4fb89ae18f completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d89551649c81908096ff392677442d completed April 10, 2026, 6:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69e8a82381708190aa0e674603d5778a completed April 22, 2026, 10:51 a.m.
NEDg Description generation batch_69e8af9665648190b7732076aa129671 completed April 22, 2026, 11:23 a.m.
NED2 Entity disambiguation (via description) batch_69ee5b3a3720819095a4a87176e052cb completed April 26, 2026, 6:36 p.m.
Created at: April 8, 2026, 9:38 p.m.