Triple

T18995571
Position Surface form Disambiguated ID Type / Status
Subject John Gilling E464799 entity
Predicate notableWork P4 FINISHED
Object The Scarlet Blade 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: The Scarlet Blade | Statement: [John Gilling, notableWork, The Scarlet Blade]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Scarlet Blade
Context triple: [John Gilling, notableWork, The Scarlet Blade]
  • A. The Scarlet Blade chosen
    The Scarlet Blade is a 1963 British historical adventure film set during the English Civil War, known for its swashbuckling action and cast including Jennifer Jayne and Oliver Reed.
  • B. Swords of Blood
    Swords of Blood is a French swashbuckling adventure film known for its spirited action and lighthearted tone, characteristic of director Philippe de Broca’s style.
  • C. The Silver Blade
    The Silver Blade is a young adult historical fantasy novel by Sally Gardner set during the French Revolution, blending romance, adventure, and elements of the supernatural.
  • D. The Flaming Sword
    "The Flaming Sword" is a 1958 British crime drama film featuring actress Patricia Dainton.
  • E. The Black Swordsman
    The Black Swordsman is the feared in-game persona of Kirito, a lone, exceptionally skilled swordsman in the virtual world of Sword Art Online.
  • 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_69d8dd01a56c81909694a128c66b21d7 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6819f8c81908bbf0448baf7e34b completed April 20, 2026, 7:32 a.m.
Created at: April 10, 2026, 12:01 p.m.