Triple

T1995
Position Surface form Disambiguated ID Type / Status
Subject Massachusetts E37 entity
Predicate borders P224 FINISHED
Object New York E550 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: New York | Statement: [Massachusetts, borders, New York]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: New York
Context triple: [Massachusetts, borders, New York]
  • A. New York chosen
    New York is a populous and economically significant U.S. state known for New York City, a global center of finance, culture, and media.
  • B. New York City
    New York City is the largest city in the United States, a global center of finance, culture, media, and technology.
  • C. Washington, D.C.
    Washington, D.C. is the capital city of the United States, serving as the nation’s political center and home to its federal government institutions.
  • D. Port of New York and New Jersey
    The Port of New York and New Jersey is the largest seaport on the U.S. East Coast and a major global shipping and transportation hub serving the New York metropolitan area.
  • E. Los Angeles
    Los Angeles is a major U.S. metropolis known for its entertainment industry, cultural diversity, and sprawling urban landscape.
  • 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_69a22cde80848190b62c5f556b4d62ba completed Feb. 27, 2026, 11:46 p.m.
NER Named-entity recognition batch_69a234ccbac88190921bd0a15e4a7dbe completed Feb. 28, 2026, 12:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69a24e51246c819098f53258d869ecde completed Feb. 28, 2026, 2:09 a.m.
Created at: Feb. 27, 2026, 11:48 p.m.