Triple

T17675525
Position Surface form Disambiguated ID Type / Status
Subject Active Job E440633 entity
Predicate supportsBackend P15794 FINISHED
Object Sucker Punch 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: Sucker Punch | Statement: [Active Job, supportsBackend, Sucker Punch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sucker Punch
Context triple: [Active Job, supportsBackend, Sucker Punch]
  • A. Sucker Punch chosen
    Sucker Punch is a 2011 fantasy action film directed by Zack Snyder that blends stylized combat sequences with surreal, dreamlike worlds.
  • B. Sucker Punch
    "Sucker Punch" is a high-energy pop single by Norwegian singer-songwriter Sigrid, known for its catchy chorus and bold, upbeat production.
  • C. Melindaou
    Melindaou is a prominent mountain peak in the Lefka Ori (White Mountains) range on the island of Crete in Greece.
  • D. Let the Right One In
    Let the Right One In is a critically acclaimed 2008 Swedish romantic horror film about the bond between a bullied boy and a mysterious child vampire.
  • E. Scott Pilgrim vs. the World
    Scott Pilgrim vs. the World is a 2010 stylized action-comedy film, based on Bryan Lee O'Malley's graphic novels, that follows a young bassist who must defeat his new girlfriend's seven evil exes in a video game-inspired world.
  • 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_69d8b9e87e18819087104a44dc4dc5b1 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e46f6cca54819094ea0bed1517724e completed April 19, 2026, 6 a.m.
Created at: April 10, 2026, 10 a.m.