Triple

T14987385
Position Surface form Disambiguated ID Type / Status
Subject Grand Paris Express E373739 entity
Predicate hasComponent P35 FINISHED
Object Line 18
Line 18 is a planned automated metro line of the Grand Paris Express project designed to improve orbital transit and connect key suburbs around Paris.
 E1135228 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 18 | Statement: [Grand Paris Express, hasComponent, Line 18]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Line 18
Context triple: [Grand Paris Express, hasComponent, Line 18]
  • A. Line 18
    Line 18 is a rapid transit line of the Shanghai Metro system serving various districts in Shanghai, China.
  • B. Line 18
    Line 18 is a planned rapid transit line of the Chongqing Metro system in Chongqing, China.
  • C. Line 18
    Line 18 is a high-speed rapid transit line of the Guangzhou Metro system in Guangzhou, China.
  • D. Line 19
    Line 19 is a north–south rapid transit line of the Beijing Subway designed to improve connectivity between the city's central districts and its outer areas.
  • E. Line 19
    Line 19 is a planned rapid transit line of the Shanghai Metro network intended to serve additional urban and suburban areas of the city.
  • 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 18
Triple: [Grand Paris Express, hasComponent, Line 18]
Generated description
Line 18 is a planned automated metro line of the Grand Paris Express project designed to improve orbital transit and connect key suburbs around Paris.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Line 18
Target entity description: Line 18 is a planned automated metro line of the Grand Paris Express project designed to improve orbital transit and connect key suburbs around Paris.
  • A. Line 18
    Line 18 is a high-speed rapid transit line of the Guangzhou Metro system in Guangzhou, China.
  • B. Line 18
    Line 18 is a rapid transit line of the Shanghai Metro system serving various districts in Shanghai, China.
  • C. Line 18
    Line 18 is a planned rapid transit line of the Chongqing Metro system in Chongqing, China.
  • D. Line 19
    Line 19 is a north–south rapid transit line of the Beijing Subway designed to improve connectivity between the city's central districts and its outer areas.
  • E. Line 19
    Line 19 is a planned rapid transit line of the Shanghai Metro network intended to serve additional urban and suburban areas of the city.
  • 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_69d85ccc84388190aa151e5173370c8d completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7007588819095bb1de029a6f2eb completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69fea5aaeda08190846c15562e67c1fb completed May 9, 2026, 3:10 a.m.
NEDg Description generation batch_69fea77a31cc8190a1737277cb826d46 completed May 9, 2026, 3:18 a.m.
NED2 Entity disambiguation (via description) batch_69fea7ecfbe881909668d2627b7892bf completed May 9, 2026, 3:20 a.m.
Created at: April 10, 2026, 2:53 a.m.