Triple

T22477551
Position Surface form Disambiguated ID Type / Status
Subject Durbanville E555672 entity
Predicate hasNeighbourhood P4813 FINISHED
Object Eversdal
Eversdal is a residential suburb in the Durbanville area of Cape Town, South Africa, known for its family-friendly environment and proximity to schools and amenities.
 E1538696 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: Eversdal | Statement: [Durbanville, hasNeighbourhood, Eversdal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Eversdal
Context triple: [Durbanville, hasNeighbourhood, Eversdal]
  • A. Undredal
    Undredal is a small, picturesque Norwegian village famed for its fjordside setting, traditional goat cheese production, and one of the world’s smallest stave churches.
  • B. Verrastranda
    Verrastranda is a village in Trøndelag county, Norway, known historically as the administrative center of the former municipality of Verran.
  • C. Thamerdal
    Thamerdal is a residential neighborhood within the Dutch town of Uithoorn in the province of North Holland.
  • D. Mortsund
    Mortsund is a small fishing village located on the island of Vestvågøy in Norway’s Lofoten archipelago.
  • E. Tyvholm
    Tyvholm is one of the small Danish islands that form part of the Hirsholmene archipelago in the Kattegat.
  • 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: Eversdal
Triple: [Durbanville, hasNeighbourhood, Eversdal]
Generated description
Eversdal is a residential suburb in the Durbanville area of Cape Town, South Africa, known for its family-friendly environment and proximity to schools and amenities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Eversdal
Target entity description: Eversdal is a residential suburb in the Durbanville area of Cape Town, South Africa, known for its family-friendly environment and proximity to schools and amenities.
  • A. Undredal
    Undredal is a small, picturesque Norwegian village famed for its fjordside setting, traditional goat cheese production, and one of the world’s smallest stave churches.
  • B. Verrastranda
    Verrastranda is a village in Trøndelag county, Norway, known historically as the administrative center of the former municipality of Verran.
  • C. Thamerdal
    Thamerdal is a residential neighborhood within the Dutch town of Uithoorn in the province of North Holland.
  • D. Mortsund
    Mortsund is a small fishing village located on the island of Vestvågøy in Norway’s Lofoten archipelago.
  • E. Tyvholm
    Tyvholm is one of the small Danish islands that form part of the Hirsholmene archipelago in the Kattegat.
  • 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_69e11e52c2048190952dc5df209b9bed completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15be58ed08190b88706a7cb85616b completed April 29, 2026, 1:16 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b125fc0a881908c72c3d711604997 completed May 18, 2026, 1:21 p.m.
NEDg Description generation batch_6a0b13dbe2708190b089b2ffb179231e completed May 18, 2026, 1:27 p.m.
NED2 Entity disambiguation (via description) batch_6a0b1462413c819086c2de0e62b2648a completed May 18, 2026, 1:30 p.m.
Created at: April 16, 2026, 8:49 p.m.