Triple
T17372788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WFF |
E422357
|
entity |
| Predicate | hasIATACode |
P2569
|
FINISHED |
| Object | WAL |
—
|
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: WAL | Statement: [WFF, hasIATACode, WAL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WAL Context triple: [WFF, hasIATACode, WAL]
-
A.
WAL
WAL is the official FIFA country code used to represent the Wales national football team in international competitions and records.
-
B.
WAL
WAL is the National Rail station code for Walton-on-Thames railway station in Surrey, England.
-
C.
WAL
chosen
WAL is the IATA airport code for the airfield serving Wallops Island, home to NASA’s Wallops Flight Facility on the eastern shore of Virginia, USA.
-
D.
WF-WAL
WF-WAL is the ISO 3166-2 subdivision code assigned to Wallis (ʻUvea), one of the main island groups of the French overseas collectivity of Wallis and Futuna in the South Pacific.
-
E.
wal
"wal" is the ISO 639-2 language code for Wolaytta, an Omotic language spoken primarily in southwestern Ethiopia.
- 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_69d889d6535c81908be333c01deaec4e |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a6a9ec881908bfe49413826d37e |
completed | April 19, 2026, 2:14 a.m. |
Created at: April 10, 2026, 5:44 a.m.