Triple
T10083532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Renton Municipal Airport |
E213962
|
entity |
| Predicate | ICAOcode |
P419
|
FINISHED |
| Object |
KRNT
KRNT is the ICAO airport code for Renton Municipal Airport, a public airport serving Renton, Washington, and known for its proximity to Boeing’s 737 assembly plant.
|
E841436
|
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: KRNT | Statement: [Renton Municipal Airport, ICAOcode, KRNT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KRNT Context triple: [Renton Municipal Airport, ICAOcode, KRNT]
-
A.
KRDU
KRDU is the ICAO airport code for Raleigh–Durham International Airport, a major commercial airport serving North Carolina’s Research Triangle region.
-
B.
KTRK
KTRK is the ICAO airport code for Truckee Tahoe Airport, a public general aviation airport serving the Truckee and Lake Tahoe region in California.
-
C.
KTHV
KTHV is a television station based in Little Rock, Arkansas, that serves as the local CBS affiliate.
-
D.
KDTW
KDTW is the ICAO airport code for Detroit Metropolitan Wayne County Airport, a major international air transport hub serving the Detroit, Michigan metropolitan area.
-
E.
KSWB-TV
KSWB-TV is a television station serving the San Diego, California market, known primarily as the local Fox network affiliate.
- 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: KRNT Triple: [Renton Municipal Airport, ICAOcode, KRNT]
Generated description
KRNT is the ICAO airport code for Renton Municipal Airport, a public airport serving Renton, Washington, and known for its proximity to Boeing’s 737 assembly plant.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: KRNT Target entity description: KRNT is the ICAO airport code for Renton Municipal Airport, a public airport serving Renton, Washington, and known for its proximity to Boeing’s 737 assembly plant.
-
A.
KRDU
KRDU is the ICAO airport code for Raleigh–Durham International Airport, a major commercial airport serving North Carolina’s Research Triangle region.
-
B.
KTRK
KTRK is the ICAO airport code for Truckee Tahoe Airport, a public general aviation airport serving the Truckee and Lake Tahoe region in California.
-
C.
KTHV
KTHV is a television station based in Little Rock, Arkansas, that serves as the local CBS affiliate.
-
D.
KDTW
KDTW is the ICAO airport code for Detroit Metropolitan Wayne County Airport, a major international air transport hub serving the Detroit, Michigan metropolitan area.
-
E.
KSWB-TV
KSWB-TV is a television station serving the San Diego, California market, known primarily as the local Fox network affiliate.
- 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_69ca839bf730819086900c323c9b8c95 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdd04352d081908f676444cd2d2578 |
completed | April 2, 2026, 2:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2b675f4b08190bd8285f210191b93 |
completed | April 5, 2026, 7:22 p.m. |
| NEDg | Description generation | batch_69d2ba645ec08190b33388a40ca7582e |
completed | April 5, 2026, 7:39 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d2babd01908190b5c9f9c3541361ee |
completed | April 5, 2026, 7:40 p.m. |
Created at: March 30, 2026, 9 p.m.