Triple
T4234697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Daytona Beach International Airport |
E94664
|
entity |
| Predicate | ICAOcode |
P419
|
FINISHED |
| Object |
KDAB
KDAB is the ICAO airport code for Daytona Beach International Airport in Daytona Beach, Florida.
|
E424820
|
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: KDAB | Statement: [Daytona Beach International Airport, ICAOcode, KDAB]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KDAB Context triple: [Daytona Beach International Airport, ICAOcode, KDAB]
-
A.
KPQI
KPQI is the ICAO airport code for Northern Maine Regional Airport at Presque Isle, a public airport serving the Presque Isle area in Maine, United States.
-
B.
KNDS
KNDS is a European defense industry holding company formed as a joint venture between Germany’s Krauss-Maffei Wegmann and France’s Nexter Systems, specializing in military land systems such as tanks and armored vehicles.
-
C.
KDAL
KDAL is the ICAO airport code for Dallas Love Field, a major airport serving the Dallas, Texas area.
-
D.
KLA
KLA is an ethnic Albanian paramilitary organization that fought for Kosovo’s independence from Serbia in the late 1990s.
-
E.
KLA
KLA is the commonly used abbreviation for the Karnataka Legislative Assembly, the lower house of the state legislature in Karnataka, India.
- 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: KDAB Triple: [Daytona Beach International Airport, ICAOcode, KDAB]
Generated description
KDAB is the ICAO airport code for Daytona Beach International Airport in Daytona Beach, Florida.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: KDAB Target entity description: KDAB is the ICAO airport code for Daytona Beach International Airport in Daytona Beach, Florida.
-
A.
KPQI
KPQI is the ICAO airport code for Northern Maine Regional Airport at Presque Isle, a public airport serving the Presque Isle area in Maine, United States.
-
B.
KNDS
KNDS is a European defense industry holding company formed as a joint venture between Germany’s Krauss-Maffei Wegmann and France’s Nexter Systems, specializing in military land systems such as tanks and armored vehicles.
-
C.
KDAL
KDAL is the ICAO airport code for Dallas Love Field, a major airport serving the Dallas, Texas area.
-
D.
KLA
KLA is an ethnic Albanian paramilitary organization that fought for Kosovo’s independence from Serbia in the late 1990s.
-
E.
KLA
KLA is the commonly used abbreviation for the Karnataka Legislative Assembly, the lower house of the state legislature in Karnataka, India.
- 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_69b34537cc6481909cd0a96acbb33ef7 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34e6705548190b695b3789d713b4a |
completed | March 12, 2026, 11:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5a8630a4481909b9835aad51614b2 |
completed | March 14, 2026, 6:26 p.m. |
| NEDg | Description generation | batch_69b5aa0d70c08190bdf890f390903139 |
completed | March 14, 2026, 6:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5ade4d2c48190990b5f3b0d99d43a |
completed | March 14, 2026, 6:50 p.m. |
Created at: March 12, 2026, 11:05 p.m.