Triple

T20309495
Position Surface form Disambiguated ID Type / Status
Subject Sandra Pullman E510197 entity
Predicate appearsIn P795 FINISHED
Object New Tricks 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: New Tricks | Statement: [Sandra Pullman, appearsIn, New Tricks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: New Tricks
Context triple: [Sandra Pullman, appearsIn, New Tricks]
  • A. New Tricks chosen
    New Tricks is a British television crime drama series about a team of retired police officers brought back to solve cold cases.
  • B. The Troubleshooters
    The Troubleshooters is a science fiction novel by Philip Latham that blends space adventure with scientifically grounded speculation.
  • C. Lie to Me
    Lie to Me is an American crime drama television series centered on a deception expert who assists law enforcement by analyzing facial expressions and body language to detect lies.
  • D. Lie to Me
    Lie to Me is a blues-rock album by American guitarist and singer Jonny Lang that helped establish him as a prominent young artist in the genre.
  • E. Watching the Detectives
    "Watching the Detectives" is a 1977 new wave/reggae-influenced single by Elvis Costello, known for its dark, cinematic lyrics and tense, off-kilter arrangement.
  • 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_69e0b4c7491c8190961113c4283b10b0 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6774286a88190800d6b062f3d7a9f completed April 20, 2026, 6:58 p.m.
Created at: April 16, 2026, 11:18 a.m.