Triple

T6138163
Position Surface form Disambiguated ID Type / Status
Subject Bombardier Cityrunner E136887 entity
Predicate marketedAs P1395 FINISHED
Object Cityrunner
Cityrunner is a low-floor light rail/tram vehicle platform developed by Bombardier for urban public transportation systems worldwide.
 E571629 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: Cityrunner | Statement: [Bombardier Cityrunner, marketedAs, Cityrunner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Cityrunner
Context triple: [Bombardier Cityrunner, marketedAs, Cityrunner]
  • A. Celine
    Celine is a French luxury fashion house known for its minimalist, modern designs in ready-to-wear, leather goods, and accessories.
  • B. Heels
    Heels is a shortened nickname commonly used to refer to the University of North Carolina Tar Heels athletic teams and their supporters.
  • C. Tailo
    Tailo is a widely used Latin-based romanization system for writing Taiwanese Hokkien, employed in education, literature, and language preservation.
  • D. Setif
    Sétif is a major city in northeastern Algeria known as an important commercial and agricultural center with a rich historical heritage.
  • E. Last Seen Wearing
    "Last Seen Wearing" is a crime novel in Colin Dexter's Inspector Morse series, featuring the detective's investigation into the disappearance of a schoolgirl.
  • 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: Cityrunner
Triple: [Bombardier Cityrunner, marketedAs, Cityrunner]
Generated description
Cityrunner is a low-floor light rail/tram vehicle platform developed by Bombardier for urban public transportation systems worldwide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Cityrunner
Target entity description: Cityrunner is a low-floor light rail/tram vehicle platform developed by Bombardier for urban public transportation systems worldwide.
  • A. Celine
    Celine is a French luxury fashion house known for its minimalist, modern designs in ready-to-wear, leather goods, and accessories.
  • B. Heels
    Heels is a shortened nickname commonly used to refer to the University of North Carolina Tar Heels athletic teams and their supporters.
  • C. Tailo
    Tailo is a widely used Latin-based romanization system for writing Taiwanese Hokkien, employed in education, literature, and language preservation.
  • D. Setif
    Sétif is a major city in northeastern Algeria known as an important commercial and agricultural center with a rich historical heritage.
  • E. Last Seen Wearing
    "Last Seen Wearing" is a crime novel in Colin Dexter's Inspector Morse series, featuring the detective's investigation into the disappearance of a schoolgirl.
  • 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_69c008a179388190a3b5a081bbf46d55 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05c83aefc8190b0e250e96f2b10b4 completed March 22, 2026, 9:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c135e78950819085a2fdd7538af4cb completed March 23, 2026, 12:45 p.m.
NEDg Description generation batch_69c138c23b7481909a647ed8565d25f2 completed March 23, 2026, 12:57 p.m.
NED2 Entity disambiguation (via description) batch_69c1391f17d08190952420bff4dd26f9 completed March 23, 2026, 12:59 p.m.
Created at: March 22, 2026, 4:15 p.m.