Triple

T7887429
Position Surface form Disambiguated ID Type / Status
Subject Claude Nicollier E183137 entity
Predicate employer P7 FINISHED
Object Swissair E205529 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: Swissair | Statement: [Claude Nicollier, employer, Swissair]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Swissair
Context triple: [Claude Nicollier, employer, Swissair]
  • A. Swissair chosen
    Swissair was the former national airline of Switzerland, renowned for its high service standards and extensive international route network until its collapse in 2001.
  • B. Swiss International Air Lines
    Swiss International Air Lines is the flag carrier airline of Switzerland, operating a global network of flights primarily from its hub in Zurich.
  • C. Austrian Airlines
    Austrian Airlines is the flag carrier airline of Austria, operating an extensive network of European and long-haul flights from its main hub in Vienna.
  • D. Interflug
    Interflug was the state-owned national airline of East Germany, operating international and domestic flights primarily within the Eastern Bloc during the Cold War.
  • E. Lufthansa
    Lufthansa is Germany’s largest airline and a major global carrier known for its extensive international network and role in shaping modern airline alliances.
  • 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_69ca828af6e48190a06ee7010d8f0e64 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb39d97460819089e37169813af5c2 completed March 31, 2026, 3:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69cbdfb5d7e08190a04dc9d3dc35a0e6 completed March 31, 2026, 2:52 p.m.
Created at: March 30, 2026, 4:59 p.m.