Triple

T17344928
Position Surface form Disambiguated ID Type / Status
Subject RPVM E421658 entity
Predicate focusCityFor P164 FINISHED
Object Philippines AirAsia 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: Philippines AirAsia | Statement: [RPVM, focusCityFor, Philippines AirAsia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Philippines AirAsia
Context triple: [RPVM, focusCityFor, Philippines AirAsia]
  • A. Philippines AirAsia chosen
    Philippines AirAsia is a low-cost airline based in the Philippines and a subsidiary of the AirAsia Group, operating domestic and international flights across Asia.
  • B. Thai AirAsia
    Thai AirAsia is a Thai low-cost airline operating domestic and international flights, and is part of the wider AirAsia group based in Southeast Asia.
  • C. AirAsia
    AirAsia is a Malaysian low-cost airline known for its extensive network of domestic and international routes across Asia and beyond.
  • D. Cebu Pacific
    Cebu Pacific is a major low-cost airline based in the Philippines, known for operating extensive domestic and regional routes across Asia.
  • E. AirAsia Indonesia
    AirAsia Indonesia is a low-cost airline based in Indonesia and a subsidiary of the Malaysia-based AirAsia Group, operating domestic and international flights across Asia.
  • 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_69d889d520008190a26917a95bf1c2ea completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a27a350819086faf12e6bf9f0e2 completed April 19, 2026, 2:12 a.m.
Created at: April 10, 2026, 5:44 a.m.