Triple

T6421795
Position Surface form Disambiguated ID Type / Status
Subject G75 Lanzhou–Haikou Expressway E127960 entity
Predicate routeNumber P1864 FINISHED
Object G75
G75 is a major Chinese national expressway route that runs between the cities of Lanzhou and Haikou.
 E591992 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: G75 | Statement: [G75 Lanzhou–Haikou Expressway, routeNumber, G75]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: G75
Context triple: [G75 Lanzhou–Haikou Expressway, routeNumber, G75]
  • A. S75
    S75 is a line of the Berlin S-Bahn urban rail network serving routes within the Berlin metropolitan area.
  • B. M75
    M75 is a densely concentrated globular star cluster in the constellation Sagittarius, cataloged by Charles Messier.
  • C. G72
    G72 is a major Chinese national expressway connecting the coastal city of Quanzhou in Fujian Province with Nanning, the capital of Guangxi Zhuang Autonomous Region.
  • D. S550
    S550 is Ford’s internal platform designation for the sixth-generation Mustang, introduced for the 2015 model year with a modernized chassis and global market focus.
  • E. M-85
    M-85 is a state trunkline highway in Michigan that runs through the Downriver suburbs of Detroit, including the city of Taylor.
  • 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: G75
Triple: [G75 Lanzhou–Haikou Expressway, routeNumber, G75]
Generated description
G75 is a major Chinese national expressway route that runs between the cities of Lanzhou and Haikou.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: G75
Target entity description: G75 is a major Chinese national expressway route that runs between the cities of Lanzhou and Haikou.
  • A. S75
    S75 is a line of the Berlin S-Bahn urban rail network serving routes within the Berlin metropolitan area.
  • B. M75
    M75 is a densely concentrated globular star cluster in the constellation Sagittarius, cataloged by Charles Messier.
  • C. G72
    G72 is a major Chinese national expressway connecting the coastal city of Quanzhou in Fujian Province with Nanning, the capital of Guangxi Zhuang Autonomous Region.
  • D. S550
    S550 is Ford’s internal platform designation for the sixth-generation Mustang, introduced for the 2015 model year with a modernized chassis and global market focus.
  • E. M-85
    M-85 is a state trunkline highway in Michigan that runs through the Downriver suburbs of Detroit, including the city of Taylor.
  • 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_69c0083815208190a9b299b8e0640218 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c06903f67c8190a1e5babeede4e183 completed March 22, 2026, 10:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69c640d8f7548190a8e0433df56b77f3 completed March 27, 2026, 8:33 a.m.
NEDg Description generation batch_69c64142633c819094c3bbdabd8f7951 completed March 27, 2026, 8:35 a.m.
NED2 Entity disambiguation (via description) batch_69c641c3d3188190bcf6bede4c90dc9d completed March 27, 2026, 8:37 a.m.
Created at: March 22, 2026, 4:43 p.m.