Triple

T2583395
Position Surface form Disambiguated ID Type / Status
Subject Frank Knox E57143 entity
Predicate familyName P18 FINISHED
Object Knox E41868 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: Knox | Statement: [Frank Knox, familyName, Knox]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Knox
Context triple: [Frank Knox, familyName, Knox]
  • A. Knox chosen
    Knox is a surname most famously associated with Henry Knox, a key American Revolutionary War general and the first United States Secretary of War.
  • B. Harrison
    Harrison is a common English surname borne by numerous notable figures across politics, the arts, and sciences.
  • C. Harrison
    Harrison is a city in New Jersey’s Hudson County, known as a residential and industrial community within the New York metropolitan area.
  • D. Pendleton
    Pendleton is an inner-city district of Salford in Greater Manchester, England, known for its mix of residential areas, retail developments, and post-war social housing.
  • E. Jackson
    Jackson is a common English surname borne by numerous notable figures across politics, science, sports, and the arts.
  • 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_69ab4a4dca6481908c301f8e317396e7 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd3c9d0548190b29743ac1d7837ff completed March 7, 2026, 7:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69af657f39dc8190971e0ad7a5396257 completed March 10, 2026, 12:27 a.m.
Created at: March 6, 2026, 9:49 p.m.