Triple

T19459973
Position Surface form Disambiguated ID Type / Status
Subject Poughkeepsie Bridge Company E486840 entity
Predicate crosses P416 FINISHED
Object Hudson River 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: Hudson River | Statement: [Poughkeepsie Bridge Company, crosses, Hudson River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hudson River
Context triple: [Poughkeepsie Bridge Company, crosses, Hudson River]
  • A. Hudson River chosen
    The Hudson River is a major waterway in eastern New York State that flows south past cities like Albany and New York City before emptying into the Atlantic Ocean at New York Harbor.
  • B. Hudson
    Hudson is a small town in Colorado, United States, located on the plains northeast of Denver.
  • C. Hudson
    Hudson is a city in Summit County, Ohio, known for its historic downtown, affluent residential character, and strong public school system.
  • D. Hudson
    Hudson is a small historic city in Columbia County, New York, known for its revitalized downtown, arts scene, and 19th-century architecture along the Hudson River.
  • E. Hudson
    Hudson is a masculine given name of English origin, traditionally meaning "son of Hugh" and commonly used in English-speaking countries.
  • 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_69d8e8d86d608190bd199a98d0297f27 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e633c7f4388190be8c207c94ba8889 completed April 20, 2026, 2:10 p.m.
Created at: April 10, 2026, 1:38 p.m.