Triple

T2212082
Position Surface form Disambiguated ID Type / Status
Subject Geneva public transport network E50939 entity
Predicate hasBoatLine P36817 FINISHED
Object M2
M2 is a boat line that operates as part of Geneva’s public transport network, providing passenger services across the city’s waters.
 E245716 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: M2 | Statement: [Geneva public transport network, hasBoatLine, M2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: M2
Context triple: [Geneva public transport network, hasBoatLine, M2]
  • A. M2
    M2 is a major British motorway that connects London with the port town of Dover in Kent, serving as an important route to the Channel ports.
  • B. M3
    M3 is a major motorway in the United Kingdom that connects London to Southampton, serving as a key route through southern England.
  • C. M20
    M20 is a major motorway in South East England connecting London to the Channel Tunnel and the port of Dover.
  • D. M
    M is a functional data mashup and query language used in Microsoft Power BI and related tools for data transformation and preparation.
  • E. M
    M is a New York City Subway service that runs along the IND Sixth Avenue Line in Manhattan and connects Brooklyn and Queens.
  • 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: M2
Triple: [Geneva public transport network, hasBoatLine, M2]
Generated description
M2 is a boat line that operates as part of Geneva’s public transport network, providing passenger services across the city’s waters.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: M2
Target entity description: M2 is a boat line that operates as part of Geneva’s public transport network, providing passenger services across the city’s waters.
  • A. M2
    M2 is a major British motorway that connects London with the port town of Dover in Kent, serving as an important route to the Channel ports.
  • B. M3
    M3 is a major motorway in the United Kingdom that connects London to Southampton, serving as a key route through southern England.
  • C. M20
    M20 is a major motorway in South East England connecting London to the Channel Tunnel and the port of Dover.
  • D. M
    M is a functional data mashup and query language used in Microsoft Power BI and related tools for data transformation and preparation.
  • E. M
    M is a New York City Subway service that runs along the IND Sixth Avenue Line in Manhattan and connects Brooklyn and Queens.
  • 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_69a88b06709c8190978fb2418470d1b6 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc5b101d48190a321625720d537b6 completed March 7, 2026, 6:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae655245c48190a37f4b6344a9a3dc completed March 9, 2026, 6:14 a.m.
NEDg Description generation batch_69ae66579c008190876ce89581337293 completed March 9, 2026, 6:19 a.m.
NED2 Entity disambiguation (via description) batch_69ae668ef8bc819085ed1c83f447d396 completed March 9, 2026, 6:19 a.m.
Created at: March 4, 2026, 7:46 p.m.