Triple

T21579996
Position Surface form Disambiguated ID Type / Status
Subject Southwest Territory E532497 entity
Predicate formerCapital P3417 FINISHED
Object Rocky Mount 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: Rocky Mount | Statement: [Southwest Territory, formerCapital, Rocky Mount]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rocky Mount
Context triple: [Southwest Territory, formerCapital, Rocky Mount]
  • A. Rocky Mount, North Carolina
    Rocky Mount, North Carolina is a mid-sized city in eastern North Carolina known historically as a railroad and tobacco hub and now as a regional center for manufacturing and healthcare.
  • B. Morganton
    Morganton is a small town located in Fannin County in the mountainous region of northern Georgia, United States.
  • C. Morganton chosen
    Morganton is a small city in Burke County, North Carolina, known as a regional hub in the foothills of the Blue Ridge Mountains with a historic downtown and proximity to outdoor recreation.
  • D. High Point
    High Point is a mountain peak in northwestern New Jersey known for its scenic views and the High Point Monument within High Point State Park.
  • E. High Point
    High Point is a residential neighborhood in the West Seattle area of Seattle, Washington, known for its large mixed-income housing redevelopment and sustainable design features.
  • 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_69e0c4618bec8190bcb0feb74568cbb1 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeeb5b8118819095fd751a03fbe8e8 completed April 27, 2026, 4:51 a.m.
Created at: April 16, 2026, 6:31 p.m.