Triple

T23149851
Position Surface form Disambiguated ID Type / Status
Subject New York State Senate District 33 E578292 entity
Predicate contains P35 FINISHED
Object Kingsbridge NE NERFINISHED

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: Kingsbridge | Statement: [New York State Senate District 33, contains, Kingsbridge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kingsbridge
Context triple: [New York State Senate District 33, contains, Kingsbridge]
  • A. Kingsbridge
    Kingsbridge is a small historic market town in the South Hams district of Devon, England, situated at the head of the Kingsbridge Estuary.
  • B. Kingsbridge chosen
    Kingsbridge is a residential neighborhood in the northwest Bronx in New York City, known for its diverse community and mix of apartment buildings and small businesses.
  • C. Ladysbridge
    Ladysbridge is a small rural village in County Cork, Ireland, known for its agricultural surroundings and proximity to the East Cork coastline.
  • D. Kingseat
    Kingseat is a small rural locality in the Auckland Region of New Zealand, known historically for its former psychiatric hospital.
  • E. Cité Plantagenêt
    Cité Plantagenêt is the historic medieval old town of Le Mans, France, known for its well-preserved architecture and ancient fortifications.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245fb8de081908f0eba7b5fd75bc4 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18ed0b76c8190ac61b949d88e9970 completed April 29, 2026, 4:53 a.m.
Created at: April 17, 2026, 4:01 p.m.