Triple

T723640
Position Surface form Disambiguated ID Type / Status
Subject Buttonwood Agreement E14672 entity
Predicate location P40 FINISHED
Object Wall Street E2854 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: Wall Street | Statement: [Buttonwood Agreement, location, Wall Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wall Street
Context triple: [Buttonwood Agreement, location, Wall Street]
  • A. Wall Street chosen
    Wall Street is the historic financial district in Lower Manhattan that serves as a global center for banking, trading, and economic power.
  • B. 40 Wall Street
    40 Wall Street is a historic neo-Gothic skyscraper in New York City's Financial District, once one of the tallest buildings in the world and later owned and branded by the Trump Organization.
  • C. New York Stock Exchange Building
    The New York Stock Exchange Building is a historic neoclassical landmark in New York City that houses the world’s largest stock exchange by market capitalization.
  • D. Hell's Kitchen
    Hell's Kitchen is a neighborhood on the West Side of Midtown Manhattan in New York City, historically known for its working-class roots and now for its vibrant dining, nightlife, and proximity to Broadway.
  • E. The Bund
    The Bund is Shanghai’s historic waterfront promenade along the Huangpu River, famed for its colonial-era architecture and iconic skyline views.
  • 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_69a4934c753c81909b309027e48b9b3a completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a5a5360c8190b16e1e4f4206d0aa completed March 1, 2026, 8:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69a6375c16488190a8509e1e2b5c6a7d completed March 3, 2026, 1:20 a.m.
Created at: March 1, 2026, 7:37 p.m.