Triple

T13325391
Position Surface form Disambiguated ID Type / Status
Subject Martinair E317427 entity
Predicate ICAOCode P419 FINISHED
Object MPH E317428 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: MPH | Statement: [Martinair, ICAOCode, MPH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MPH
Context triple: [Martinair, ICAOCode, MPH]
  • A. MPH chosen
    MPH is the ICAO airline designator assigned to Martinair, a Dutch cargo and former passenger airline based in the Netherlands.
  • B. MPH
    MPH is a creator-owned superhero comic series written by Mark Millar, published under his Millarworld imprint, that follows a group of Detroit teens who gain super-speed from a mysterious drug.
  • C. Master of Public Health
    The Master of Public Health is a graduate-level professional degree focused on developing expertise in public health practice, research, and policy to improve population health outcomes.
  • D. Doctor of Public Health
    The Doctor of Public Health (DrPH) is an advanced professional doctoral degree focused on developing leadership, policy, and practice expertise to address complex public health challenges.
  • E. BUSPH
    BUSPH is the graduate-level public health school of Boston University, known for its research, education, and training in population health and health policy.
  • 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_69d806b4d62c81908d4ced1665414be5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d9992c1fec8190bcb6a6bb3c973a24 completed April 11, 2026, 12:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69f71f2cd5688190a2a0db0f0295de83 completed May 3, 2026, 10:10 a.m.
Created at: April 9, 2026, 9:30 p.m.