Triple

T13365590
Position Surface form Disambiguated ID Type / Status
Subject Haines Airport E318929 entity
Predicate ICAOcode P419 FINISHED
Object PAHN
PAHN is the ICAO airport code for Haines Airport, a public airport serving the community of Haines in Alaska, United States.
E1036998 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: PAHN | Statement: [Haines Airport, ICAOcode, PAHN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PAHN
Context triple: [Haines Airport, ICAOcode, PAHN]
  • A. PH
    PH is the vehicle registration code used on license plates for vehicles registered in Ploiești, Romania.
  • B. PH
    PH is a postcode area in the United Kingdom covering Perth and surrounding parts of central and northern Scotland.
  • C. PAH
    PAH is the three-letter IATA airport code for Barkley Regional Airport in Paducah, Kentucky, United States.
  • D. PAN
    PAN is an experimental music project known for its dark, atmospheric sound and collaboration with electronic producer The Haxan Cloak.
  • E. PAN
    PAN is the vehicle registration code assigned to the district of Rottal-Inn in Bavaria, Germany, which includes the town of Simbach am Inn.
  • 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: PAHN
Triple: [Haines Airport, ICAOcode, PAHN]
Generated description
PAHN is the ICAO airport code for Haines Airport, a public airport serving the community of Haines in Alaska, United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: PAHN
Target entity description: PAHN is the ICAO airport code for Haines Airport, a public airport serving the community of Haines in Alaska, United States.
  • A. PH
    PH is the vehicle registration code used on license plates for vehicles registered in Ploiești, Romania.
  • B. PH
    PH is a postcode area in the United Kingdom covering Perth and surrounding parts of central and northern Scotland.
  • C. PAH
    PAH is the three-letter IATA airport code for Barkley Regional Airport in Paducah, Kentucky, United States.
  • D. PAN
    PAN is the vehicle registration code assigned to the district of Rottal-Inn in Bavaria, Germany, which includes the town of Simbach am Inn.
  • E. PAN
    PAN is an experimental music project known for its dark, atmospheric sound and collaboration with electronic producer The Haxan Cloak.
  • 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_69d806b7bbac8190b85278c87fa7aff3 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69da628c71ac81908cfa36342077766e completed April 11, 2026, 3:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7267e9d608190b36f58a92d4a9964 completed May 3, 2026, 10:42 a.m.
NEDg Description generation batch_69f72807bae081909f7e66657c03b841 completed May 3, 2026, 10:48 a.m.
NED2 Entity disambiguation (via description) batch_69f728afff888190a82e3d4f4fad717b completed May 3, 2026, 10:51 a.m.
Created at: April 9, 2026, 9:32 p.m.