Triple

T16412943
Position Surface form Disambiguated ID Type / Status
Subject PZL Świdnik E398609 entity
Predicate product P490 FINISHED
Object PZL W-3 Sokół E398609 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: PZL W-3 Sokół | Statement: [PZL Świdnik, product, PZL W-3 Sokół]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PZL W-3 Sokół
Context triple: [PZL Świdnik, product, PZL W-3 Sokół]
  • A. PZL.23 Karaś
    The PZL.23 Karaś was a Polish single-engine light bomber and reconnaissance aircraft used by the Polish Air Force in the late 1930s and during the early stages of World War II.
  • B. PZL Świdnik chosen
    PZL Świdnik is a major Polish aerospace manufacturer best known for producing helicopters and other aircraft, and is a key part of Poland’s defense and aviation industry.
  • C. PZL.50 Jastrząb
    The PZL.50 Jastrząb was a late-1930s Polish single-seat monoplane fighter aircraft developed to modernize Poland’s air force on the eve of World War II.
  • D. PZL-130 Orlik
    The PZL-130 Orlik is a Polish-designed turboprop trainer aircraft used primarily for pilot training and aerobatic display by the Polish Air Force.
  • E. PZL-104 Wilga
    The PZL-104 Wilga is a Polish short takeoff and landing (STOL) utility aircraft widely used for roles such as glider towing, parachute training, and general aviation tasks.
  • 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_69d87f2950248190bc8ad9b9bebdc8c8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32875bad08190bc3e2218df8c1b07 completed April 18, 2026, 6:45 a.m.
NED1 Entity disambiguation (via context triple) batch_6a004f457b8c8190b278697ef43301cb completed May 10, 2026, 9:26 a.m.
Created at: April 10, 2026, 5:09 a.m.