Triple

T23143258
Position Surface form Disambiguated ID Type / Status
Subject South African National Route network E577516 entity
Predicate includesRoute P4374 FINISHED
Object N93
N93 is a designated national route within South Africa’s numbered highway system.
 E1576047 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: N93 | Statement: [South African National Route network, includesRoute, N93]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: N93
Context triple: [South African National Route network, includesRoute, N93]
  • A. N93
    The N93 is a Nokia smartphone from the mid-2000s known for its swivel design and advanced video recording capabilities for its time.
  • B. N92
    N92 is a designated national route within South Africa’s numbered highway system, forming part of the country’s primary road network.
  • C. N92
    N92 is a Nokia smartphone model known for its early support of mobile TV and multimedia features.
  • D. N98
    N98 is the ICAO airport code assigned to Boyne City Municipal Airport, a public general aviation facility serving Boyne City, Michigan.
  • E. N98
    N98 is the Federal Aviation Administration (FAA) location identifier assigned to Boyne City Municipal Airport in Michigan, United States.
  • 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: N93
Triple: [South African National Route network, includesRoute, N93]
Generated description
N93 is a designated national route within South Africa’s numbered highway system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: N93
Target entity description: N93 is a designated national route within South Africa’s numbered highway system.
  • A. N93
    The N93 is a Nokia smartphone from the mid-2000s known for its swivel design and advanced video recording capabilities for its time.
  • B. N92
    N92 is a designated national route within South Africa’s numbered highway system, forming part of the country’s primary road network.
  • C. N92
    N92 is a Nokia smartphone model known for its early support of mobile TV and multimedia features.
  • D. N98
    N98 is the ICAO airport code assigned to Boyne City Municipal Airport, a public general aviation facility serving Boyne City, Michigan.
  • E. N98
    N98 is the Federal Aviation Administration (FAA) location identifier assigned to Boyne City Municipal Airport in Michigan, United States.
  • 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_69e245f8e6248190ba3d58e068b4dccb completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18ecc3710819088ac5d72dad0459a completed April 29, 2026, 4:53 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c3f3d44a8819086dc22a62313de0b completed May 19, 2026, 10:45 a.m.
NEDg Description generation batch_6a0c3fec592c8190a8d8ae47f310edd7 completed May 19, 2026, 10:48 a.m.
NED2 Entity disambiguation (via description) batch_6a0c4064012c819083b2ffe795226ab6 completed May 19, 2026, 10:50 a.m.
Created at: April 17, 2026, 4 p.m.