Triple

T9260968
Position Surface form Disambiguated ID Type / Status
Subject Marlborough Region E222576 entity
Predicate hasTown P847 FINISHED
Object Picton E410852 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: Picton | Statement: [Marlborough Region, hasTown, Picton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Picton
Context triple: [Marlborough Region, hasTown, Picton]
  • A. Picton chosen
    Picton is a small coastal town in New Zealand’s South Island that serves as a major ferry terminal and gateway between the islands.
  • B. Picton
    Picton is a small town in Prince Edward County, Ontario, known as a local hub for visitors exploring nearby parks, wineries, and Lake Ontario beaches.
  • C. La Punta
    La Punta is a small coastal district of the Constitutional Province of Callao in Peru, known for its beaches, historic architecture, and naval and port-related activities.
  • D. Fish Hoek
    Fish Hoek is a coastal suburb and popular beach town on the False Bay shoreline of Cape Town, South Africa, known for its family-friendly swimming beach and relaxed residential character.
  • E. Port Clements
    Port Clements is a small village on Graham Island in Haida Gwaii, British Columbia, known historically for its forestry industry and access to outdoor recreation.
  • 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_69ca841f2e808190a64f4c31903a1332 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd07175be881908a917573ec9b9081 completed April 1, 2026, 11:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69d09bfb7dfc8190bc337a54083e0dd9 completed April 4, 2026, 5:04 a.m.
Created at: March 30, 2026, 7:32 p.m.