Triple

T20645160
Position Surface form Disambiguated ID Type / Status
Subject Scanline VFX E507335 entity
Predicate workedOnProduction P100406 FINISHED
Object Battleship (film) 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: Battleship (film) | Statement: [Scanline VFX, workedOnProduction, Battleship (film)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Battleship (film)
Context triple: [Scanline VFX, workedOnProduction, Battleship (film)]
  • A. Battleship chosen
    Battleship is a 2012 science fiction naval war film loosely inspired by the classic board game, featuring an alien invasion and large-scale maritime combat.
  • B. film "Battleship"
    The film "Battleship" is a 2012 science fiction naval war movie loosely based on the classic board game, featuring a U.S. fleet battling an alien invasion.
  • C. Battleship No. 1
    Battleship No. 1 was the original designation for the Imperial Japanese Navy’s Nagato, a pioneering fast battleship that served as a flagship and symbol of Japan’s naval power in the early 20th century.
  • D. The Marine
    The Marine is a 2006 action film starring professional wrestler and actor John Cena as a former Marine on a mission to rescue his kidnapped wife.
  • E. Convoy
    Convoy is a technology-driven freight and logistics startup that built a digital marketplace to connect shippers with trucking carriers.
  • 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_69e0b4be702c8190a3d2410a881d310a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6af1dd79481909de985d03ab861c2 completed April 20, 2026, 10:56 p.m.
Created at: April 16, 2026, 11:43 a.m.