Triple

T1839524
Position Surface form Disambiguated ID Type / Status
Subject PATH train system E41140 entity
Predicate connectsCity P4245 FINISHED
Object Harrison E118958 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: Harrison | Statement: [PATH train system, connectsCity, Harrison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harrison
Context triple: [PATH train system, connectsCity, Harrison]
  • A. Harrison
    Harrison is a common English surname borne by numerous notable figures across politics, the arts, and sciences.
  • B. Harrison chosen
    Harrison is a city in New Jersey’s Hudson County, known as a residential and industrial community within the New York metropolitan area.
  • C. Knox
    Knox is a surname most famously associated with Henry Knox, a key American Revolutionary War general and the first United States Secretary of War.
  • D. Hamilton
    Hamilton is a major inland city in New Zealand’s Waikato region, known for its role as an agricultural, educational, and commercial hub on the North Island.
  • E. Hamilton
    Hamilton is a large town in South Lanarkshire, Scotland, historically known as a key administrative and market center in the region.
  • 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_69a88647f9388190909bc36e795bdaec completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb03b3eb08190ae68d8476fc89c7f completed March 7, 2026, 4:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69adc9bb92a88190a00b102d3be0383c completed March 8, 2026, 7:10 p.m.
Created at: March 4, 2026, 7:33 p.m.