Triple

T19167573
Position Surface form Disambiguated ID Type / Status
Subject Gimpo–Shanghai Hongqiao route E469225 entity
Predicate airportCodeDestination P45615 FINISHED
Object SHA 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: SHA | Statement: [Gimpo–Shanghai Hongqiao route, airportCodeDestination, SHA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SHA
Context triple: [Gimpo–Shanghai Hongqiao route, airportCodeDestination, SHA]
  • A. SHA chosen
    SHA is the IATA airport code for Shanghai Hongqiao International Airport, a major domestic and regional aviation hub serving Shanghai, China.
  • B. SHA
    SHA is the commonly used abbreviation for the School of Hospitality Administration, an academic institution focused on hospitality and related fields.
  • C. SHA
    SHA is the vehicle registration code for the German district of Schwäbisch Hall in the state of Baden-Württemberg.
  • D. SHA
    SHA is the commonly used abbreviation for the Maryland State Highway Administration, the state agency responsible for planning, building, and maintaining Maryland’s state highway system.
  • E. SSHHA
    SSHHA is a musical project or band connected to English rock drummer Zak Starkey, known for his work with acts like The Who and Oasis.
  • 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_69d8dd09d5a081909ae43c286651ae5a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f16035b481908667a4415a1a63c9 completed April 20, 2026, 9:26 a.m.
Created at: April 10, 2026, 12:06 p.m.