Triple

T21551639
Position Surface form Disambiguated ID Type / Status
Subject Mayor of Portland, Maine E531774 entity
Predicate seat P75 FINISHED
Object Portland City Hall 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: Portland City Hall | Statement: [Mayor of Portland, Maine, seat, Portland City Hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Portland City Hall
Context triple: [Mayor of Portland, Maine, seat, Portland City Hall]
  • A. Portland City Hall chosen
    Portland City Hall is the historic municipal government building and architectural landmark serving the city of Portland, Maine.
  • B. Portland City Hall
    Portland City Hall is the historic municipal building in downtown Portland, Oregon, that houses the offices and chambers of the city’s government.
  • C. Seattle City Hall
    Seattle City Hall is the modern civic headquarters of the City of Seattle, Washington, known for its contemporary glass-and-steel architecture and public plaza in the downtown area.
  • D. Portland Building
    The Portland Building is a landmark postmodern office building in downtown Portland, Oregon, designed by architect Michael Graves and noted for its colorful, ornamental façade.
  • E. Portland Building
    The Portland Building is a key academic and administrative facility on the University of Portsmouth campus, housing teaching spaces, student services, and various university departments.
  • 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_69e0c460232c81908de2c3819d17c00e completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeb59375f481909d9e2b66d18c7c32 completed April 27, 2026, 1:02 a.m.
Created at: April 16, 2026, 6:29 p.m.