Triple

T20789893
Position Surface form Disambiguated ID Type / Status
Subject SZG E511744 entity
Predicate threeLetterCode P418 FINISHED
Object SZG 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: SZG | Statement: [SZG, threeLetterCode, SZG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SZG
Context triple: [SZG, threeLetterCode, SZG]
  • A. SZG chosen
    SZG is the three-letter IATA airport code for Salzburg Airport in Salzburg, Austria.
  • B. SZS
    SZS is the ICAO airline designator assigned to SAS Ireland, a subsidiary carrier operating flights on behalf of Scandinavian Airlines.
  • C. SZL
    SZL is the ISO 4217 currency code for the Swazi lilangeni, the official currency of Eswatini.
  • D. SZL
    SZL is the IATA airport code for Whiteman Air Force Base, a United States Air Force installation in Missouri.
  • E. SZF
    SZF is the commonly used abbreviation for the Faculty of Social Sciences at the University of Latvia, encompassing disciplines such as sociology, communication, and political science.
  • 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_69e0b4cb83948190bd57bec21d78ed53 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c28f0e1081909f18dddfc6ec084c completed April 21, 2026, 12:19 a.m.
Created at: April 16, 2026, 12:38 p.m.