Triple

T22467907
Position Surface form Disambiguated ID Type / Status
Subject KORH E555407 entity
Predicate hasIATAcode P2569 FINISHED
Object ORH 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: ORH | Statement: [KORH, hasIATAcode, ORH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ORH
Context triple: [KORH, hasIATAcode, ORH]
  • A. ORH chosen
    ORH is the IATA airport code for Worcester Regional Airport, a public airport serving Worcester, Massachusetts, and the surrounding region.
  • B. OHR
    OHR is the international body overseeing the civilian implementation of the Dayton Peace Agreement in Bosnia and Herzegovina.
  • C. ORU
    ORU is the IATA airport code for Juan Mendoza Airport, a regional airport serving the city of Oruro in Bolivia.
  • D. ORU
    ORU is a private Christian liberal arts university in Tulsa, Oklahoma, founded by evangelist Oral Roberts and known for integrating faith-based education with a diverse range of academic programs.
  • E. ORR
    ORR is the independent regulator and competition authority for Britain’s railways and the monitor of National Highways in England.
  • 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_69e11e51fdec8190adfdf9f8a6362221 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15bdda62c8190937ac13a4481b4b7 completed April 29, 2026, 1:16 a.m.
Created at: April 16, 2026, 8:48 p.m.