Triple

T3518269
Position Surface form Disambiguated ID Type / Status
Subject Alstom Citadis E74358 entity
Predicate hasVariant P455 FINISHED
Object Citadis 402
The Citadis 402 is a low-floor, multi-section light rail tram model produced by Alstom for modern urban transit systems.
 E376638 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: Citadis 402 | Statement: [Alstom Citadis, hasVariant, Citadis 402]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Citadis 402
Context triple: [Alstom Citadis, hasVariant, Citadis 402]
  • A. Citadis 304
    The Citadis 304 is a low-floor light rail tram model produced by Alstom for modern urban public transport networks.
  • B. Grand Paris project
    The Grand Paris project is a major French urban development and transportation initiative aimed at transforming the Paris metropolitan area through new infrastructure, housing, and economic hubs.
  • C. Alstom Metropolis
    Alstom Metropolis is a family of modern, high-capacity metro trains manufactured by Alstom and used in urban rapid transit systems worldwide.
  • D. Cité
    Cité is a Paris Métro station located on the Île de la Cité in the historic center of Paris.
  • E. Port Vauban
    Port Vauban is a major Mediterranean marina in Antibes, France, renowned as one of Europe’s largest harbours for luxury yachts and pleasure boats.
  • 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: Citadis 402
Triple: [Alstom Citadis, hasVariant, Citadis 402]
Generated description
The Citadis 402 is a low-floor, multi-section light rail tram model produced by Alstom for modern urban transit systems.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Citadis 402
Target entity description: The Citadis 402 is a low-floor, multi-section light rail tram model produced by Alstom for modern urban transit systems.
  • A. Citadis 304
    The Citadis 304 is a low-floor light rail tram model produced by Alstom for modern urban public transport networks.
  • B. Grand Paris project
    The Grand Paris project is a major French urban development and transportation initiative aimed at transforming the Paris metropolitan area through new infrastructure, housing, and economic hubs.
  • C. Alstom Metropolis
    Alstom Metropolis is a family of modern, high-capacity metro trains manufactured by Alstom and used in urban rapid transit systems worldwide.
  • D. Cité
    Cité is a Paris Métro station located on the Île de la Cité in the historic center of Paris.
  • E. Port Vauban
    Port Vauban is a major Mediterranean marina in Antibes, France, renowned as one of Europe’s largest harbours for luxury yachts and pleasure boats.
  • 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_69ad85cfb5c881909c9a2edd9d6043cc completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adbc32f90081908960acb3e94402be completed March 8, 2026, 6:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69b44eeb831481909f9def02fe995c69 completed March 13, 2026, 5:52 p.m.
NEDg Description generation batch_69b4542260108190a3ffa515dbd6f545 completed March 13, 2026, 6:14 p.m.
NED2 Entity disambiguation (via description) batch_69b482dfdfc08190a20e58707368b573 completed March 13, 2026, 9:34 p.m.
Created at: March 8, 2026, 3:19 p.m.