Triple
T22537670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yakutsk Airport |
E557198
|
entity |
| Predicate | ICAOCode |
P419
|
FINISHED |
| Object | UEEE |
—
|
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: UEEE | Statement: [Yakutsk Airport, ICAOCode, UEEE]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UEEE Context triple: [Yakutsk Airport, ICAOCode, UEEE]
-
A.
UEEE
chosen
UEEE is the ICAO airport code for Yakutsk Airport, a major air transport hub in the Sakha Republic of Russia.
-
B.
EEUM
EEUM is the engineering school of the University of Minho in Portugal, offering education and research across multiple engineering disciplines.
-
C.
UUEE
UUEE is the ICAO airport code for Sheremetyevo International Airport, one of Moscow’s primary international air hubs in Russia.
-
D.
UEI
UEI (Unique Entity Identifier) is a 12-character alphanumeric ID used by the U.S. federal government to uniquely identify organizations doing business with it, particularly for grants and contracts.
-
E.
EEPU
EEPU is the ICAO airport code for the Port of Tallinn’s associated airfield in Estonia.
- 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_69e11e57483c8190b0887c4f8ff26446 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15f2f671c8190b7a7d9b6d0d64a9b |
completed | April 29, 2026, 1:30 a.m. |
Created at: April 16, 2026, 8:51 p.m.