Triple

T10097294
Position Surface form Disambiguated ID Type / Status
Subject Island Council E215900 entity
Predicate appliesToSettlement P8239 FINISHED
Object Adamstown E215897 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: Adamstown | Statement: [Island Council, appliesToSettlement, Adamstown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adamstown
Context triple: [Island Council, appliesToSettlement, Adamstown]
  • A. Adamstown chosen
    Adamstown is the small, remote settlement that serves as the only town and administrative center of the Pitcairn Islands in the South Pacific Ocean.
  • B. Bradentown
    Bradentown was the original name of the city now known as Bradenton, Florida, a Gulf Coast community in Manatee County.
  • C. Martintown
    Martintown is a small rural community located within the Township of South Glengarry in eastern Ontario, Canada.
  • D. Robertstown
    Robertstown is a small Irish village in County Kildare known for its historic canal-side setting and heritage as a former inland waterways hub.
  • E. Shingletown
    Shingletown is a small rural community in Northern California known for its forested setting near Lassen Volcanic National Park.
  • 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_69ca83a4947c8190823a7495dc5d96ed completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd07ad40081909610a7a8dc836651 completed April 2, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d30050fbec8190ab7807d64ab73e61 completed April 6, 2026, 12:37 a.m.
Created at: March 30, 2026, 9:02 p.m.