Triple
T19424593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wigan Wallgate railway station |
E485947
|
entity |
| Predicate | stationCode |
P1289
|
FINISHED |
| Object | WGW |
—
|
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: WGW | Statement: [Wigan Wallgate railway station, stationCode, WGW]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WGW Context triple: [Wigan Wallgate railway station, stationCode, WGW]
-
A.
WGW
chosen
WGW is the National Rail station code for Wigan Wallgate railway station in Greater Manchester, England.
-
B.
GWW
GWW is the IATA airport code for Gatow Airfield, a former military airfield in Berlin, Germany.
-
C.
WGB
WGB is the abbreviated name for Working Group B, a committee-style body typically focused on specialized tasks or policy areas within a larger organization.
-
D.
GWA
GWA is the public utility agency responsible for providing water and wastewater services across the island of Guam.
-
E.
HGW
HGW is the vehicle registration code used on license plates for the city of Greifswald in northeastern Germany.
- 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_69d8e8d688f881909c85104a62e09d8a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63217bd2c81909e216e13aa4c487d |
completed | April 20, 2026, 2:03 p.m. |
Created at: April 10, 2026, 1:37 p.m.