Triple

T6062848
Position Surface form Disambiguated ID Type / Status
Subject Swann Covered Bridge E135077 entity
Predicate nearSettlement P3883 FINISHED
Object Rosa, Alabama E229392 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: Rosa, Alabama | Statement: [Swann Covered Bridge, nearSettlement, Rosa, Alabama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rosa, Alabama
Context triple: [Swann Covered Bridge, nearSettlement, Rosa, Alabama]
  • A. Rosa, Alabama chosen
    Rosa, Alabama is a small town located in Blount County in the northern part of the state.
  • B. Grant, Alabama
    Grant, Alabama is a small town in Marshall County known as the closest community to Cathedral Caverns State Park in the Appalachian region of northern Alabama.
  • C. Steele, Alabama
    Steele, Alabama is a small town in northeastern Alabama known for its rural character and location within St. Clair County.
  • D. Roanoke, Alabama
    Roanoke, Alabama is a small city in eastern Alabama known for its rural character and role as a local commercial and community hub.
  • E. Riverside, Alabama
    Riverside, Alabama is a small community in St. Clair County known for its location along the Coosa River in central Alabama.
  • 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_69c00878d06881909ee78e88913bf890 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c05722815081909ee47e8f94b87b3a completed March 22, 2026, 8:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69c11d1e61188190aea0e2b1945ca682 completed March 23, 2026, 10:59 a.m.
Created at: March 22, 2026, 4:10 p.m.