Triple

T4855027
Position Surface form Disambiguated ID Type / Status
Subject Duluth International Airport E108515 entity
Predicate IATAcode P418 FINISHED
Object DLH
DLH is the IATA airport code for Duluth International Airport, a commercial and general aviation airport serving Duluth, Minnesota, and the surrounding region.
 E475034 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: DLH | Statement: [Duluth International Airport, IATAcode, DLH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DLH
Context triple: [Duluth International Airport, IATAcode, DLH]
  • A. DLH
    DLH is the ICAO airline designator used for Lufthansa, Germany's largest and flag carrier airline.
  • B. Dellner
    Dellner is a company specializing in railway coupling and connection systems used on modern passenger and freight trains worldwide.
  • C. DLG
    DLG is the vehicle registration code for the municipality of Blindheim in Germany.
  • D. D.N.H.
    D.N.H. is the standard legal abbreviation for the United States District Court for the District of New Hampshire, a federal trial court within the First Circuit.
  • E. DLS
    DLS is a conference that forms part of the SPLASH event, focusing on research and advances in dynamic languages and their applications.
  • 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: DLH
Triple: [Duluth International Airport, IATAcode, DLH]
Generated description
DLH is the IATA airport code for Duluth International Airport, a commercial and general aviation airport serving Duluth, Minnesota, and the surrounding region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DLH
Target entity description: DLH is the IATA airport code for Duluth International Airport, a commercial and general aviation airport serving Duluth, Minnesota, and the surrounding region.
  • A. DLH
    DLH is the ICAO airline designator used for Lufthansa, Germany's largest and flag carrier airline.
  • B. Dellner
    Dellner is a company specializing in railway coupling and connection systems used on modern passenger and freight trains worldwide.
  • C. DLG
    DLG is the vehicle registration code for the municipality of Blindheim in Germany.
  • D. D.N.H.
    D.N.H. is the standard legal abbreviation for the United States District Court for the District of New Hampshire, a federal trial court within the First Circuit.
  • E. DLS
    DLS is a conference that forms part of the SPLASH event, focusing on research and advances in dynamic languages and their applications.
  • 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_69bd440a89548190a5f14ba6da6b97dc completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6d3c9d7881908c04cef2cb7db745 completed March 20, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69be5ce7385c8190897fd2343c0ebeed completed March 21, 2026, 8:55 a.m.
NEDg Description generation batch_69be5dadcec88190bf9a272c4a9aef9a completed March 21, 2026, 8:58 a.m.
NED2 Entity disambiguation (via description) batch_69be6159ff7c8190baa116240f76dea5 completed March 21, 2026, 9:14 a.m.
Created at: March 20, 2026, 1:26 p.m.