Triple
T19579733
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skien Airport, Geiteryggen |
E489954
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object | SKE |
—
|
NE NERFINISHED |
How this triple was built (2 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: SKE | Statement: [Skien Airport, Geiteryggen, IATAcode, SKE]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SKE Context triple: [Skien Airport, Geiteryggen, IATAcode, SKE]
-
A.
SKE
chosen
SKE is the National Rail station code for Skewen railway station in Neath Port Talbot, Wales.
-
B.
Ske
Ske is an Oceanic language spoken by indigenous communities on Pentecost Island in Vanuatu.
-
C.
SKO
SKO is the abbreviation for the Saito Kinen Orchestra, a renowned Japanese classical ensemble founded by conductor Seiji Ozawa in honor of his teacher Hideo Saito.
-
D.
SKO
SKO is the IATA airport code for Sadiq Abubakar III International Airport serving Sokoto, Nigeria.
-
E.
SKW
SKW is Poland’s Military Counterintelligence Service, responsible for protecting the armed forces and state defense structures from espionage, terrorism, and other security threats.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8dd9374819098e36349b3211663 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6402763b8819099e535979f094f9d |
completed | April 20, 2026, 3:03 p.m. |
Created at: April 10, 2026, 1:42 p.m.