Triple

T13783281
Position Surface form Disambiguated ID Type / Status
Subject oil-drop experiment E331182 entity
Predicate performedBy P1363 FINISHED
Object Harvey Fletcher E145405 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: Harvey Fletcher | Statement: [oil-drop experiment, performedBy, Harvey Fletcher]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harvey Fletcher
Context triple: [oil-drop experiment, performedBy, Harvey Fletcher]
  • A. Harvey Fletcher chosen
    Harvey Fletcher was an American physicist and acoustical engineer renowned as a pioneer of stereophonic sound and psychoacoustics.
  • B. Dewey Finn
    Dewey Finn is an enthusiastic, slacker musician who poses as a substitute teacher and forms a rock band with his students in the comedy film "School of Rock."
  • C. Ralph Winters
    Ralph Winters was a film editor known for his work on numerous Hollywood movies across several decades.
  • D. Max Drummey
    Max Drummey is an American musician best known as the guitarist and co-founder of the indie pop band Chester French.
  • E. Harry Starks
    Harry Starks is a fictional gay East End gangster and nightclub owner in 1960s–70s London, best known as the charismatic, ruthless antihero of Jake Arnott’s crime novel "The Long Firm."
  • 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_69d81c58feb08190a77bca8bf7d6d20f completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0247ccc881908dad7b547221f15d completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b07b0b2881909b316e3cc67f1ec1 completed May 3, 2026, 8:30 p.m.
Created at: April 9, 2026, 10:11 p.m.