Triple

T17964887
Position Surface form Disambiguated ID Type / Status
Subject Tessa Ross E449176 entity
Predicate notableWork P4 FINISHED
Object Submarine 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: Submarine | Statement: [Tessa Ross, notableWork, Submarine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Submarine
Context triple: [Tessa Ross, notableWork, Submarine]
  • A. Submarine
    "Submarine" is a track from the musical score of the James Bond film "For Your Eyes Only," composed by Bill Conti.
  • B. Submarine
    "Submarine" is a song by Icelandic artist Björk from her experimental, largely a cappella 2004 album Medúlla.
  • C. Submarine chosen
    "Submarine" is a 2010 coming-of-age comedy-drama film, based on Joe Dunthorne’s novel, in which Noah Taylor plays a key supporting role.
  • D. Sottomarina
    Sottomarina is a coastal district and popular seaside resort area of the Venetian town of Chioggia in northeastern Italy.
  • E. Submarino Amarillo
    Submarino Amarillo is the popular nickname of Spanish football club Cádiz CF, referencing their distinctive yellow kit and resilient, underdog identity.
  • 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_69d8b9f9927c8190a006110c8b996e61 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4b136e4088190ac97fd92dc84a4b9 completed April 19, 2026, 10:40 a.m.
Created at: April 10, 2026, 10:22 a.m.