Triple

T20339141
Position Surface form Disambiguated ID Type / Status
Subject Experiment Perilous E495692 entity
Predicate screenplayBy P15305 FINISHED
Object Robert Blees 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: Robert Blees | Statement: [Experiment Perilous, screenplayBy, Robert Blees]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Blees
Context triple: [Experiment Perilous, screenplayBy, Robert Blees]
  • A. Robert Blees chosen
    Robert Blees was an American screenwriter and producer known for his work on mid-20th-century Hollywood films and television series.
  • B. Leonard Bleecker
    Leonard Bleecker was an early American broker and financier known for being among the original founders of what became the New York Stock Exchange.
  • C. Edward Leede
    Edward Leede was a notable Dartmouth College basketball player and benefactor after whom Dartmouth’s Leede Arena is named.
  • D. William Bartels
    William Bartels is an individual known primarily by the name William “Bill” Bartels, though further widely recognized biographical or professional details are not clearly established.
  • E. Paul Bruhn
    Paul Bruhn is a historic preservation advocate known for his long-time leadership of the Preservation Trust of Vermont, where he worked to revitalize downtowns and protect the state's architectural heritage.
  • 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_69e0b4a1a09881908d97270d6971a25a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e678342a0081908ede8006eb5506a3 completed April 20, 2026, 7:02 p.m.
Created at: April 16, 2026, 11:23 a.m.