Triple

T16698142
Position Surface form Disambiguated ID Type / Status
Subject The Crooked Way E405772 entity
Predicate director P255 FINISHED
Object Robert Florey E215311 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: Robert Florey | Statement: [The Crooked Way, director, Robert Florey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Florey
Context triple: [The Crooked Way, director, Robert Florey]
  • A. Robert Florey chosen
    Robert Florey was a French-American film director and screenwriter known for his work in early Hollywood horror and experimental cinema.
  • B. Lewis Maurice Schanfield
    Lewis Maurice Schanfield, better known as Lew Fields, was a prominent American vaudeville comedian, actor, and theatrical producer of the late 19th and early 20th centuries.
  • C. Frank Losee
    Frank Losee was an American stage and silent film actor active in the early 20th century.
  • D. Harold Butz
    Harold Butz is an individual notable enough to be specifically cited as a bearer of the surname Butz.
  • E. George C. Schatz
    George C. Schatz is an American theoretical chemist renowned for his contributions to reaction dynamics, nanoscience, and computational chemistry.
  • 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_69d8838db21081909589220fd71440a4 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3832f550c8190bf7514d4611dec6a completed April 18, 2026, 1:12 p.m.
NED1 Entity disambiguation (via context triple) batch_6a009d36aa90819090b738c1c94dcb9f completed May 10, 2026, 2:59 p.m.
Created at: April 10, 2026, 5:19 a.m.