Triple

T23018092
Position Surface form Disambiguated ID Type / Status
Subject Terror by Night E573086 entity
Predicate starring P1507 FINISHED
Object Skelton Knaggs 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: Skelton Knaggs | Statement: [Terror by Night, starring, Skelton Knaggs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Skelton Knaggs
Context triple: [Terror by Night, starring, Skelton Knaggs]
  • A. Skelton Knaggs chosen
    Skelton Knaggs was a British character actor known for his distinctive, sinister appearance and roles in 1940s Hollywood horror and thriller films.
  • B. Skelton
    Skelton is a surname most famously associated with American comedian and entertainer Red Skelton.
  • C. Skelton
    Skelton is a small village and civil parish in the East Riding of Yorkshire, England.
  • D. Jack Marrowbone
    Jack Marrowbone is the central protagonist of the 2017 psychological horror film "The Secret of Marrowbone," around whom the story’s family mystery and supernatural elements revolve.
  • E. Edwin Clayhanger
    Edwin Clayhanger is the introspective, dutiful protagonist of Arnold Bennett’s novel "Clayhanger," whose life chronicles the struggles and aspirations of a young man in an English provincial town during the late 19th century.
  • 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_69e245b764cc8190a51be76f1d9611e1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183e64a4c8190b8d29ed638c7fef8 completed April 29, 2026, 4:07 a.m.
Created at: April 17, 2026, 3:52 p.m.