Triple

T23143239
Position Surface form Disambiguated ID Type / Status
Subject South African National Route network E577516 entity
Predicate includesRoute P4374 FINISHED
Object N63
N63 is a designated national route within South Africa’s highway system, forming part of the country’s primary road transport network.
 E1574435 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: N63 | Statement: [South African National Route network, includesRoute, N63]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: N63
Context triple: [South African National Route network, includesRoute, N63]
  • A. N62
    N62 is a major Dutch roadway in the province of Zeeland that connects key transport routes and includes the Westerscheldetunnel under the Western Scheldt.
  • B. N366
    N366 is a regional road in the Netherlands that serves as a key connection route for traffic to and from the municipality of Pekela in the province of Groningen.
  • C. N363
    N363 is a regional road in the Netherlands that connects the village of Usquert with other nearby towns in the province of Groningen.
  • D. N60
    N60 is a major regional road in Belgium that connects several towns and provides important access to the national road network.
  • E. N316
    N316 is a regional Dutch road that connects the town of Doetinchem with other nearby areas in the Netherlands.
  • 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: N63
Triple: [South African National Route network, includesRoute, N63]
Generated description
N63 is a designated national route within South Africa’s highway system, forming part of the country’s primary road transport network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: N63
Target entity description: N63 is a designated national route within South Africa’s highway system, forming part of the country’s primary road transport network.
  • A. N62
    N62 is a major Dutch roadway in the province of Zeeland that connects key transport routes and includes the Westerscheldetunnel under the Western Scheldt.
  • B. N366
    N366 is a regional road in the Netherlands that serves as a key connection route for traffic to and from the municipality of Pekela in the province of Groningen.
  • C. N363
    N363 is a regional road in the Netherlands that connects the village of Usquert with other nearby towns in the province of Groningen.
  • D. N60
    N60 is a major regional road in Belgium that connects several towns and provides important access to the national road network.
  • E. N316
    N316 is a regional Dutch road that connects the town of Doetinchem with other nearby areas in the Netherlands.
  • 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_6a0c3091b7b8819083d7fd257275bdd0 completed May 19, 2026, 9:42 a.m.
NEDg Description generation batch_6a0c317030c481908991f978ca15085e completed May 19, 2026, 9:46 a.m.
NED2 Entity disambiguation (via description) batch_6a0c322595308190b33c9e09fb26c2cc completed May 19, 2026, 9:49 a.m.
Created at: April 17, 2026, 4 p.m.