Triple

T11432473
Position Surface form Disambiguated ID Type / Status
Subject Taipei–Hong Kong E270918 entity
Predicate servedByCarrier P3844 FINISHED
Object HK Express E49553 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: HK Express | Statement: [Taipei–Hong Kong, servedByCarrier, HK Express]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HK Express
Context triple: [Taipei–Hong Kong, servedByCarrier, HK Express]
  • A. HK Express chosen
    HK Express is a Hong Kong-based low-cost airline operating regional flights across Asia.
  • B. Airphil Express
    Airphil Express was a Philippine low-cost airline that operated domestic and regional flights before being rebranded as PAL Express, a subsidiary of Philippine Airlines.
  • C. UP Express
    UP Express is a dedicated airport rail link in Toronto that provides fast, frequent train service between Union Station downtown and Toronto Pearson International Airport.
  • D. National Express
    National Express is a major UK-based coach and bus operator providing long-distance and local passenger transport services domestically and internationally.
  • E. Sky Express
    Sky Express is a Greek regional airline that operates domestic flights connecting numerous islands and mainland cities within Greece.
  • 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_69d6aadeef688190874bcecd88b3dd9b completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d808855a7481909314f90ad92aae68 completed April 9, 2026, 8:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5d36cee548190a8215ba088bdb01a completed April 20, 2026, 7:19 a.m.
Created at: April 8, 2026, 9:35 p.m.