Triple

T3782556
Position Surface form Disambiguated ID Type / Status
Subject OPUS card E85452 entity
Predicate validOn P4464 FINISHED
Object RTL buses
RTL buses are public transit vehicles operated by Réseau de transport de Longueuil serving the South Shore region of Greater Montreal.
 E389661 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: RTL buses | Statement: [OPUS card, validOn, RTL buses]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: RTL buses
Context triple: [OPUS card, validOn, RTL buses]
  • A. SL buses
    SL buses are the public bus services operating within the Stockholm County public transport network in Sweden.
  • B. RTC buses
    RTC buses are the public transit buses operated by Réseau de transport de la Capitale serving the Quebec City region in Canada.
  • C. RTP buses
    RTP buses are a publicly operated bus network in Mexico City that provides surface transit services and connections to the city’s metro system.
  • D. Movia buses
    Movia buses are the primary public bus network in the Copenhagen region, providing extensive urban and regional transport services that integrate with the city’s metro and rail systems.
  • E. STM bus network
    The STM bus network is the extensive system of urban bus routes serving neighborhoods across the island of Montreal as part of the city’s public transit infrastructure.
  • 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: RTL buses
Triple: [OPUS card, validOn, RTL buses]
Generated description
RTL buses are public transit vehicles operated by Réseau de transport de Longueuil serving the South Shore region of Greater Montreal.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: RTL buses
Target entity description: RTL buses are public transit vehicles operated by Réseau de transport de Longueuil serving the South Shore region of Greater Montreal.
  • A. SL buses
    SL buses are the public bus services operating within the Stockholm County public transport network in Sweden.
  • B. RTC buses
    RTC buses are the public transit buses operated by Réseau de transport de la Capitale serving the Quebec City region in Canada.
  • C. RTP buses
    RTP buses are a publicly operated bus network in Mexico City that provides surface transit services and connections to the city’s metro system.
  • D. Movia buses
    Movia buses are the primary public bus network in the Copenhagen region, providing extensive urban and regional transport services that integrate with the city’s metro and rail systems.
  • E. STM bus network
    The STM bus network is the extensive system of urban bus routes serving neighborhoods across the island of Montreal as part of the city’s public transit infrastructure.
  • 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_69aed937fa8881908208ef3801060826 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aee3db11108190aa81ee8ed22709fe completed March 9, 2026, 3:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb19229c8190a6f0ee4ae7f52dab completed March 14, 2026, 6:07 a.m.
NEDg Description generation batch_69b4fbacc8dc8190bb7e4a14e2d2f504 completed March 14, 2026, 6:09 a.m.
NED2 Entity disambiguation (via description) batch_69b4fc1f679881908e63b22d910c532b completed March 14, 2026, 6:11 a.m.
Created at: March 9, 2026, 3:13 p.m.