Triple

T12835753
Position Surface form Disambiguated ID Type / Status
Subject Houghton E306906 entity
Predicate adjacentTo P224 FINISHED
Object Parktown E593310 NE FINISHED

How this triple was built (2 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: Parktown | Statement: [Houghton, adjacentTo, Parktown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Parktown
Context triple: [Houghton, adjacentTo, Parktown]
  • A. Parktown chosen
    Parktown is a historic, affluent suburb of Johannesburg, South Africa, known for its early 20th-century architecture, tree-lined streets, and proximity to the city’s central business and academic districts.
  • B. River Hill
    River Hill is a residential village and community within the planned city of Columbia, Maryland.
  • C. Druid Hills
    Druid Hills is a historic, affluent residential neighborhood in Atlanta, Georgia, known for its early 20th-century architecture, landscaped parks, and proximity to Emory University.
  • D. Woodbrook
    Woodbrook is a district in Port of Spain, Trinidad and Tobago, known for its mix of residential areas, commercial activity, and major sporting and entertainment venues.
  • E. Laurel Heights
    Laurel Heights is a San Francisco neighborhood that hosts one of the University of California, San Francisco’s satellite campus sites, known for its mix of residential streets and institutional buildings.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d7bdf52b94819096d6f0ba4ab50a98 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96fb1c7248190bb6e644e041d192e completed April 10, 2026, 9:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f68edaa6288190a775f6e852fa941b completed May 2, 2026, 11:55 p.m.
Created at: April 9, 2026, 5:35 p.m.