Triple

T22071572
Position Surface form Disambiguated ID Type / Status
Subject Sam Donaldson E545419 entity
Predicate reportedFrom P9386 FINISHED
Object Capitol Hill 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: Capitol Hill | Statement: [Sam Donaldson, reportedFrom, Capitol Hill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Capitol Hill
Context triple: [Sam Donaldson, reportedFrom, Capitol Hill]
  • A. Capitol Hill chosen
    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.
  • B. 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.
  • C. 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.
  • D. Capitol Hill
    Capitol Hill is a historic, densely populated Denver neighborhood known for its eclectic mix of old mansions, apartments, arts venues, and vibrant nightlife.
  • E. Capitol Hill
    Capitol Hill is a prominent district in Monrovia, Liberia, known as the country’s political center and seat of key government institutions.
  • 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_69e11e344dfc81909b1d88a7221329c7 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12888dcc08190b18d3d44d09ab943 completed April 28, 2026, 9:37 p.m.
Created at: April 16, 2026, 8:28 p.m.