Triple

T20011312
Position Surface form Disambiguated ID Type / Status
Subject Swan Point Cemetery E494594 entity
Predicate burialPlaceOf P196 FINISHED
Object Rowland G. Hazard 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: Rowland G. Hazard | Statement: [Swan Point Cemetery, burialPlaceOf, Rowland G. Hazard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rowland G. Hazard
Context triple: [Swan Point Cemetery, burialPlaceOf, Rowland G. Hazard]
  • A. Rowland G. Hazard chosen
    Rowland G. Hazard was a 19th-century American industrialist, politician, and social reformer from Rhode Island known for his work in manufacturing, anti-slavery efforts, and public service.
  • B. Henry T. Hazard
    Henry T. Hazard was a 19th-century American lawyer and politician who served as mayor of Los Angeles, California.
  • C. Philip DeGuere
    Philip DeGuere was an American television producer, writer, and director best known for his work on popular series in the 1970s and 1980s.
  • D. John Havens
    John Havens is an American businessman and former Citigroup executive who co-founded the investment firm Old Lane Partners.
  • E. Carl Hovey
    Carl Hovey was an American magazine editor and writer active in the early 20th century, known for his work in literary and popular periodicals.
  • 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_69da626b2d748190886981ea90c8b2ea completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e662362df48190abf16129eea39985 completed April 20, 2026, 5:28 p.m.
Created at: April 11, 2026, 3:33 p.m.