Triple

T17871258
Position Surface form Disambiguated ID Type / Status
Subject Deering Airport E446840 entity
Predicate IATACode P418 FINISHED
Object DRG
DRG is the IATA airport code for Deering Airport, a public airport serving the community of Deering in Alaska, United States.
E1292056 NE FINISHED

How this triple was built (4 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: DRG | Statement: [Deering Airport, IATACode, DRG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DRG
Context triple: [Deering Airport, IATACode, DRG]
  • A. DDS
    DDS is the California state agency responsible for overseeing services and supports for individuals with developmental disabilities.
  • B. DDS
    DDS is the state agency in Massachusetts responsible for providing services and supports to individuals with intellectual and developmental disabilities.
  • C. DDS
    DDS is the stock ticker symbol for Dillard's, an American department store chain.
  • D. DDS
    DDS (Data Distribution Service) is a real-time, publish–subscribe middleware standard for scalable, high-performance data exchange in distributed systems.
  • E. DDS
    DDS is a professional doctoral degree in dentistry that qualifies graduates to practice as licensed dentists.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: DRG
Triple: [Deering Airport, IATACode, DRG]
Generated description
DRG is the IATA airport code for Deering Airport, a public airport serving the community of Deering in Alaska, United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: DRG
Target entity description: DRG is the IATA airport code for Deering Airport, a public airport serving the community of Deering in Alaska, United States.
  • A. DDS
    DDS is the California state agency responsible for overseeing services and supports for individuals with developmental disabilities.
  • B. DDS
    DDS is the state agency in Massachusetts responsible for providing services and supports to individuals with intellectual and developmental disabilities.
  • C. DDS
    DDS is the stock ticker symbol for Dillard's, an American department store chain.
  • D. DDS
    DDS (Data Distribution Service) is a real-time, publish–subscribe middleware standard for scalable, high-performance data exchange in distributed systems.
  • E. DDS
    DDS is a professional doctoral degree in dentistry that qualifies graduates to practice as licensed dentists.
  • F. None of above. chosen

Provenance (5 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_69d8b9f4c22c819093c2680434472894 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49aa30ff8819090c51c1d7767e952 completed April 19, 2026, 9:04 a.m.
NED1 Entity disambiguation (via context triple) batch_6a030c6d0fdc8190afbff57b4b8290b8 completed May 12, 2026, 11:18 a.m.
NEDg Description generation batch_6a030d0529f081908d5fd390af9d6bb7 completed May 12, 2026, 11:20 a.m.
NED2 Entity disambiguation (via description) batch_6a030dbb23208190bb73c4f9cee76f73 completed May 12, 2026, 11:23 a.m.
Created at: April 10, 2026, 10:18 a.m.