Triple

T19669408
Position Surface form Disambiguated ID Type / Status
Subject Not a Bad Thing E472292 entity
Predicate writer P1360 FINISHED
Object Jerome Harmon 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: Jerome Harmon | Statement: [Not a Bad Thing, writer, Jerome Harmon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jerome Harmon
Context triple: [Not a Bad Thing, writer, Jerome Harmon]
  • A. Jerome Harmon chosen
    Jerome Harmon is an American record producer and songwriter known for his work on major hip-hop and R&B projects alongside top artists and fellow producers.
  • B. Laurie Olin
    Laurie Olin is a prominent American landscape architect and urban designer known for shaping major public spaces in cities across the United States.
  • C. Charles Gwathmey
    Charles Gwathmey was a prominent American modernist architect known for his influential residential designs and as a key member of the New York Five.
  • D. Kevin Roche
    Kevin Roche was an acclaimed Irish-American architect known for his innovative modernist designs and influential large-scale public and corporate buildings.
  • E. Arthur Erickson
    Arthur Erickson was a renowned Canadian architect celebrated for his modernist designs that harmonize buildings with their surrounding landscapes.
  • 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_69d8e514f2e08190ba70a4449519d218 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6416ad1b481908d2890d8c21aac5c completed April 20, 2026, 3:08 p.m.
Created at: April 10, 2026, 1:45 p.m.