Triple

T11528539
Position Surface form Disambiguated ID Type / Status
Subject Swift F.4 E273358 entity
Predicate improvementOver P6555 FINISHED
Object Swift F.3 E912429 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: Swift F.3 | Statement: [Swift F.4, improvementOver, Swift F.3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Swift F.3
Context triple: [Swift F.4, improvementOver, Swift F.3]
  • A. Swift F.3 chosen
    The Swift F.3 was a later, improved variant of the British Supermarine Swift jet fighter, featuring upgraded performance and systems over its predecessors.
  • B. Swift F.1
    The Swift F.1 was an early production variant of the British Supermarine Swift jet fighter, used briefly by the Royal Air Force in the 1950s.
  • C. Swift F.7
    The Swift F.7 was a later, improved variant of the British Supermarine Swift jet fighter, incorporating refinements in performance and equipment over earlier marks.
  • D. Swift F.2
    The Swift F.2 was an early production fighter variant of the British Supermarine Swift jet, featuring improved armament and performance over the initial models.
  • E. Swift F.4
    The Swift F.4 was a later, improved fighter variant of the British Supermarine Swift jet, featuring enhanced performance and handling over earlier models.
  • 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_69d6aae3fbec8190a14632a5df2538b6 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d883972b10819093bd09cf8406671c completed April 10, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69f018b2f394819084c3cfd589098c30 completed April 28, 2026, 2:17 a.m.
Created at: April 8, 2026, 9:37 p.m.