Triple
T7273881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terminal 2 (Dublin Airport) |
E162975
|
entity |
| Predicate | IATAAirportCode |
P418
|
FINISHED |
| Object | DUB |
E153718
|
NE FINISHED |
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: DUB | Statement: [Terminal 2 (Dublin Airport), IATAAirportCode, DUB]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DUB Context triple: [Terminal 2 (Dublin Airport), IATAAirportCode, DUB]
-
A.
DUB
chosen
DUB is the three-letter IATA airport code for Dublin Airport, the main international gateway to Dublin and the Republic of Ireland.
-
B.
U-Dub
U-Dub is a common nickname for the University of Washington, a major public research university in Seattle known for its strong academic and athletic programs.
-
C.
DUS
DUS is the three-letter IATA code for Düsseldorf Airport, a major international airport in western Germany.
-
D.
Didube
Didube is a metro station in Tbilisi, Georgia, serving as a key transit hub that connects the city’s metro system with major bus and marshrutka routes to other regions.
-
E.
Debub
Debub is a southern administrative region of Eritrea known for its highland landscapes, agriculture, and historical sites.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69c6885c5964819085b209701769877f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eb0de9f48190807dd148758bad62 |
completed | March 27, 2026, 8:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7db2936dc8190aed38888bb5e47b8 |
completed | March 28, 2026, 1:44 p.m. |
Created at: March 27, 2026, 2:58 p.m.