Triple

T5458897
Position Surface form Disambiguated ID Type / Status
Subject Kingston Fortifications E122546 entity
Predicate hasPart P35 FINISHED
Object Fort Henry E22422 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: Fort Henry | Statement: [Kingston Fortifications, hasPart, Fort Henry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fort Henry
Context triple: [Kingston Fortifications, hasPart, Fort Henry]
  • A. Fort Henry chosen
    Fort Henry is a historic 19th-century British military fortress and popular tourist site located in Kingston, Ontario, Canada.
  • B. Fort Hancock
    Fort Hancock is a historic former U.S. Army coastal defense installation located on Sandy Hook in New Jersey, now preserved as part of Gateway National Recreation Area.
  • C. Pittsburg Landing
    Pittsburg Landing is a riverside location on the Tennessee River that served as the primary Union landing and staging area during the American Civil War’s Battle of Shiloh.
  • D. Mount Juliet
    Mount Juliet is a rapidly growing suburban city in Wilson County, Tennessee, located just east of Nashville.
  • E. Fort Hawkins
    Fort Hawkins was an early 19th-century U.S. military fort and frontier trading post that became the nucleus for the later city of Macon, Georgia.
  • 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_69bd46424248819085282ddf50a565f3 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd91f353c481909ae1a73ae419fb9a completed March 20, 2026, 6:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf4149c6c081909f57e214dad54777 completed March 22, 2026, 1:09 a.m.
Created at: March 20, 2026, 2:08 p.m.