Triple

T11296639
Position Surface form Disambiguated ID Type / Status
Subject Capitol portico E267468 entity
Predicate faces P1699 FINISHED
Object Capitol Square unclear NED1 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: Capitol Square | Statement: [Capitol portico, faces, Capitol Square]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Capitol Square
Context triple: [Capitol portico, faces, Capitol Square]
  • A. Capitol Square
    Capitol Square is a prominent public area surrounding the United States Capitol that serves as a central site for government, civic events, and tourism in Washington, D.C.
  • B. Capitol Square
    Capitol Square is the central public plaza and surrounding streets in downtown Madison, Wisconsin, that form the civic and commercial heart of the city around the state capitol building.
  • C. Capitol Square
    Capitol Square is the landscaped governmental plaza and surrounding grounds that encompass the Kansas State Capitol building in Topeka.
  • D. Capitol Square
    Capitol Square is the prominent civic and governmental center of Columbus, Ohio, surrounding the Ohio Statehouse in the heart of downtown.
  • E. Capitol Square
    Capitol Square is a historic park and government complex in Richmond, Virginia, that serves as the landscaped setting for the Virginia State Capitol and several other important state buildings and monuments.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69d6aac993a08190a6f36445ebaf9a43 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e9a262e08190a7c1eacbc6019496 completed April 9, 2026, 6:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69e525a842dc81909c84d8bd1a6414fa completed April 19, 2026, 6:57 p.m.
Created at: April 8, 2026, 9:32 p.m.