Triple

T15305872
Position Surface form Disambiguated ID Type / Status
Subject Career Girls E365895 entity
Predicate hasCastMember P2308 FINISHED
Object Andy Serkis E46056 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: Andy Serkis | Statement: [Career Girls, hasCastMember, Andy Serkis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andy Serkis
Context triple: [Career Girls, hasCastMember, Andy Serkis]
  • A. Andy Serkis chosen
    Andy Serkis is a British actor and filmmaker best known for his pioneering motion-capture performances, particularly as Gollum in The Lord of the Rings film trilogy.
  • B. Sonny Serkis
    Sonny Serkis is a British actor and the son of acclaimed performer and director Andy Serkis.
  • C. Hugh Lloyd
    Hugh Lloyd was a British character actor and comedian best known for his work in mid-20th-century film and television, particularly in comic roles.
  • D. Warwick Davis
    Warwick Davis is an English actor best known for his roles in fantasy and science-fiction films such as "Willow," the "Harry Potter" series, and the "Star Wars" franchise.
  • E. Douglas Henshall
    Douglas Henshall is a Scottish actor best known for his roles in the TV series "Primeval" and "Shetland."
  • 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_69d85a113ee881908e297a1d38dd79fa completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03ccef14c819099c5ebe962e7f867 completed April 16, 2026, 1:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69fef89d961481909be8dcc2864982c9 completed May 9, 2026, 9:04 a.m.
Created at: April 10, 2026, 3:16 a.m.