Triple

T14154698
Position Surface form Disambiguated ID Type / Status
Subject Old Parliament House E350784 entity
Predicate locatedOn P40 FINISHED
Object Capital Hill E69857 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: Capital Hill | Statement: [Old Parliament House, locatedOn, Capital Hill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Capital Hill
Context triple: [Old Parliament House, locatedOn, Capital Hill]
  • A. Capital Hill chosen
    Capital Hill is a prominent elevated area in Canberra that serves as the symbolic and geographic center of Australia’s federal government district.
  • B. Capitol Hill
    Capitol Hill is a prominent district in Salt Lake City that serves as Utah’s political center and overlooks the downtown area.
  • C. Capitol Hill
    Capitol Hill is a historic Washington, D.C. neighborhood that houses the U.S. Capitol and serves as a central hub of American political life.
  • D. Capitol Hill
    Capitol Hill is a residential neighbourhood in the city of Burnaby, British Columbia, known for its hillside location and views over the surrounding region.
  • E. Capitol Hill
    Capitol Hill is a dense, historically significant Seattle neighborhood known for its vibrant nightlife, LGBTQ+ community, arts scene, and eclectic mix of shops and restaurants.
  • 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_69d8278775fc8190b0802d22ca2f495d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6133754881908e1e97db71772deb completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd19395924819084d78815c3f12f43 completed May 7, 2026, 10:59 p.m.
Created at: April 10, 2026, 12:58 a.m.