Triple

T488263
Position Surface form Disambiguated ID Type / Status
Subject Pennsylvania Avenue E9927 entity
Predicate hasLandmark P105 FINISHED
Object Trump International Hotel Washington, D.C. (former Old Post Office)
Trump International Hotel Washington, D.C. (formerly the Old Post Office) is a luxury hotel housed in a historic late-19th-century federal building located between the White House and the U.S. Capitol.
E61029 NE FINISHED

How this triple was built (4 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: Trump International Hotel Washington, D.C. (former Old Post Office) | Statement: [Pennsylvania Avenue, hasLandmark, Trump International Hotel Washington, D.C. (former Old Post Office)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Trump International Hotel Washington, D.C. (former Old Post Office)
Context triple: [Pennsylvania Avenue, hasLandmark, Trump International Hotel Washington, D.C. (former Old Post Office)]
  • A. Trump International Hotel & Tower
    Trump International Hotel & Tower is a luxury skyscraper hotel and residential building brand associated with former U.S. President Donald Trump, featuring high-end accommodations and prominent locations in major cities.
  • B. Herbert C. Hoover Building
    The Herbert C. Hoover Building is a prominent federal office building in Washington, D.C., best known as the headquarters of the U.S. Department of Commerce.
  • C. Eisenhower Executive Office Building
    The Eisenhower Executive Office Building is a historic, French Second Empire–style government building in Washington, D.C., that houses much of the White House staff and key offices of the Executive Office of the President.
  • D. Harry S. Truman Building
    The Harry S. Truman Building is a large federal office building in Washington, D.C., that houses the main offices and leadership of the U.S. foreign affairs apparatus.
  • E. J. Edgar Hoover Building
    The J. Edgar Hoover Building is a large Brutalist-style office complex in Washington, D.C., that serves as the main headquarters of the FBI.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Trump International Hotel Washington, D.C. (former Old Post Office)
Triple: [Pennsylvania Avenue, hasLandmark, Trump International Hotel Washington, D.C. (former Old Post Office)]
Generated description
Trump International Hotel Washington, D.C. (formerly the Old Post Office) is a luxury hotel housed in a historic late-19th-century federal building located between the White House and the U.S. Capitol.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Trump International Hotel Washington, D.C. (former Old Post Office)
Target entity description: Trump International Hotel Washington, D.C. (formerly the Old Post Office) is a luxury hotel housed in a historic late-19th-century federal building located between the White House and the U.S. Capitol.
  • A. Trump International Hotel & Tower
    Trump International Hotel & Tower is a luxury skyscraper hotel and residential building brand associated with former U.S. President Donald Trump, featuring high-end accommodations and prominent locations in major cities.
  • B. Herbert C. Hoover Building
    The Herbert C. Hoover Building is a prominent federal office building in Washington, D.C., best known as the headquarters of the U.S. Department of Commerce.
  • C. Eisenhower Executive Office Building
    The Eisenhower Executive Office Building is a historic, French Second Empire–style government building in Washington, D.C., that houses much of the White House staff and key offices of the Executive Office of the President.
  • D. Harry S. Truman Building
    The Harry S. Truman Building is a large federal office building in Washington, D.C., that houses the main offices and leadership of the U.S. foreign affairs apparatus.
  • E. J. Edgar Hoover Building
    The J. Edgar Hoover Building is a large Brutalist-style office complex in Washington, D.C., that serves as the main headquarters of the FBI.
  • F. None of above. chosen

Provenance (5 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_69a2e802e2908190ab17c9479e0b6412 completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2f0df764481909811d9483dfbc4aa completed Feb. 28, 2026, 1:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69a47471e5ac8190acfed4803183f11a completed March 1, 2026, 5:16 p.m.
NEDg Description generation batch_69a476527a6881909cc06330ae6bcbcb completed March 1, 2026, 5:24 p.m.
NED2 Entity disambiguation (via description) batch_69a4769c31f081909bc74682ed6fd9d6 completed March 1, 2026, 5:25 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.