Triple

T19941063
Position Surface form Disambiguated ID Type / Status
Subject Harpies E479306 entity
Predicate alsoKnownAs P39 FINISHED
Object Snatchers E728288 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: Snatchers | Statement: [Harpies, alsoKnownAs, Snatchers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Snatchers
Context triple: [Harpies, alsoKnownAs, Snatchers]
  • A. Snatchers chosen
    Snatchers are roving gangs of bounty hunters in the Harry Potter series who track down and capture Muggle-borns and other targets for Voldemort’s regime.
  • B. Snatched
    Snatched is a 2017 comedy film starring Goldie Hawn and Amy Schumer as a mother-daughter duo whose tropical vacation goes disastrously off course.
  • C. Snatch
    Snatch is a 2000 British crime comedy film directed by Guy Ritchie, known for its fast-paced, interwoven plot, dark humor, and ensemble cast including Jason Statham and Brad Pitt.
  • D. Sneaky Pete
    Sneaky Pete is an American crime drama television series about a con man who assumes his former cellmate’s identity to escape his past, starring Giovanni Ribisi.
  • E. Heist
    Heist is a 2001 crime thriller film written and directed by David Mamet, centered on a veteran thief forced into one last high-stakes robbery.
  • 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_69d8e522a17c819095165d4d24939fd8 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65a1a8df4819094e84855465df6c0 completed April 20, 2026, 4:53 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07f6eebbb0819087108b2c76e15af1 completed May 16, 2026, 4:47 a.m.
Created at: April 10, 2026, 1:54 p.m.