Triple

T8883758
Position Surface form Disambiguated ID Type / Status
Subject Saint-Lazare E211473 entity
Predicate metroLine P848 FINISHED
Object Line 13
Line 13 is one of the busiest and most congested lines of the Paris Métro, running north–south across the city and serving major hubs such as Saint-Lazare.
 E765956 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: Line 13 | Statement: [Saint-Lazare, metroLine, Line 13]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Line 13
Context triple: [Saint-Lazare, metroLine, Line 13]
  • A. Line 13
    Line 13 is a suburban loop line of the Beijing Subway that serves the northern part of the city and connects several major transfer stations.
  • B. Line 13
    Line 13 is a rapid transit line of the Guangzhou Metro system in Guangzhou, China.
  • C. Line 13
    Line 13 is a major rapid transit route in the Shanghai Metro system that serves key urban districts and supports heavy commuter traffic across the city.
  • D. Line 13
    Line 13 is a planned rapid transit line of the Shenzhen Metro system in Shenzhen, China.
  • E. Line 14
    Line 14 is a rapid transit line of the Shenzhen Metro system in Shenzhen, China, serving as part of the city's expanding urban rail network.
  • 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: Line 13
Triple: [Saint-Lazare, metroLine, Line 13]
Generated description
Line 13 is one of the busiest and most congested lines of the Paris Métro, running north–south across the city and serving major hubs such as Saint-Lazare.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Line 13
Target entity description: Line 13 is one of the busiest and most congested lines of the Paris Métro, running north–south across the city and serving major hubs such as Saint-Lazare.
  • A. Line 13
    Line 13 is a suburban loop line of the Beijing Subway that serves the northern part of the city and connects several major transfer stations.
  • B. Line 13
    Line 13 is a rapid transit line of the Guangzhou Metro system in Guangzhou, China.
  • C. Line 13
    Line 13 is a major rapid transit route in the Shanghai Metro system that serves key urban districts and supports heavy commuter traffic across the city.
  • D. Line 13
    Line 13 is a planned rapid transit line of the Shenzhen Metro system in Shenzhen, China.
  • E. Line 14
    Line 14 is a fully automated, high-capacity line of the Paris Métro known for its modern trains and role in relieving congestion on central routes.
  • 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_69ca838f9e20819096ab1f236a70381a completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc616b2d988190b923ef1e33aab787 completed April 1, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfba1b1bec8190ab667a0c5dba3513 completed April 3, 2026, 1:01 p.m.
NEDg Description generation batch_69cfbbf8ff388190beef5f8f1e6935c6 completed April 3, 2026, 1:09 p.m.
NED2 Entity disambiguation (via description) batch_69cfbc570c28819087bea8058c4b08a9 completed April 3, 2026, 1:10 p.m.
Created at: March 30, 2026, 6:53 p.m.