Triple

T18605522
Position Surface form Disambiguated ID Type / Status
Subject Zeerust E454732 entity
Predicate roadConnection P385 FINISHED
Object N4
N4 is a major national highway in South Africa that forms part of the key east–west transport corridor linking Gauteng to Botswana and Mozambique.
 E1332798 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: N4 | Statement: [Zeerust, roadConnection, N4]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: N4
Context triple: [Zeerust, roadConnection, N4]
  • A. N4
    N4 is the station code used to identify the Midtown station on Atlanta’s MARTA rapid transit system.
  • B. N40
    N40 is a major national primary road in County Cork, Ireland, forming part of the city’s southern ring route and linking key radial routes around Cork.
  • C. N1
    N1 is a central London postcode district covering parts of Islington, Hoxton, and surrounding areas known for their vibrant urban character.
  • D. N1
    N1 is a major national highway route, typically serving as a primary north–south or intercity transport corridor in the country’s road network.
  • E. N3
    N3 is a Dutch regional road that serves as a key connector route in the South Holland region of 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: N4
Triple: [Zeerust, roadConnection, N4]
Generated description
N4 is a major national highway in South Africa that forms part of the key east–west transport corridor linking Gauteng to Botswana and Mozambique.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: N4
Target entity description: N4 is a major national highway in South Africa that forms part of the key east–west transport corridor linking Gauteng to Botswana and Mozambique.
  • A. N4
    N4 is the station code used to identify the Midtown station on Atlanta’s MARTA rapid transit system.
  • B. N40
    N40 is a major national primary road in County Cork, Ireland, forming part of the city’s southern ring route and linking key radial routes around Cork.
  • C. N1
    N1 is a central London postcode district covering parts of Islington, Hoxton, and surrounding areas known for their vibrant urban character.
  • D. N1
    N1 is a major national highway route, typically serving as a primary north–south or intercity transport corridor in the country’s road network.
  • E. N3
    N3 is a Dutch regional road that serves as a key connector route in the South Holland region of 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_69d8d38bbe7c8190bdec3138e7d413c9 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e547544a248190a3465e22dfb29305 completed April 19, 2026, 9:21 p.m.
NED1 Entity disambiguation (via context triple) batch_6a05038573588190a825b00e3f210c3f completed May 13, 2026, 11:04 p.m.
NEDg Description generation batch_6a05044722c88190bdeac36b602673e9 completed May 13, 2026, 11:07 p.m.
NED2 Entity disambiguation (via description) batch_6a0504deb488819086f3146141b3fb45 completed May 13, 2026, 11:10 p.m.
Created at: April 10, 2026, 11:45 a.m.