Triple

T2457738
Position Surface form Disambiguated ID Type / Status
Subject Errol E54460 entity
Predicate hasVariant P455 FINISHED
Object Erroll E54460 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: Erroll | Statement: [Errol, hasVariant, Erroll]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Erroll
Context triple: [Errol, hasVariant, Erroll]
  • A. Errol chosen
    Errol is a masculine given name of English origin, often used as a first name in various English-speaking countries.
  • B. Dooley Wilson
    Dooley Wilson was an American actor and singer best known for his iconic performance as Sam, the piano player who sings "As Time Goes By," in the classic film Casablanca.
  • C. Bobby Short
    Bobby Short was an American cabaret singer and pianist renowned for his sophisticated interpretations of the Great American Songbook, especially the works of Cole Porter.
  • D. Mickey Jones
    Mickey Jones was an American drummer and character actor known for his work with prominent rock bands in the 1960s and 1970s and for numerous film and television roles.
  • E. Elmo Williams
    Elmo Williams was an American film editor and producer best known for his Academy Award–winning work on "High Noon" and contributions to numerous classic Hollywood films.
  • 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_69ab49dee84c819096b50a0049c347ac completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd10860188190bfc4c554914487b4 completed March 7, 2026, 7:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69af17932530819097caefff366e2183 completed March 9, 2026, 6:55 p.m.
Created at: March 6, 2026, 9:44 p.m.