Triple
T19315899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cwmbran railway station |
E483095
|
entity |
| Predicate | stationCode |
P1289
|
FINISHED |
| Object | CWM |
—
|
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: CWM | Statement: [Cwmbran railway station, stationCode, CWM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CWM Context triple: [Cwmbran railway station, stationCode, CWM]
-
A.
CWM
chosen
CWM is the National Rail station code for Cwmbran railway station in Torfaen, Wales.
-
B.
CWM
CWM is the ICAO airport code assigned to Air Marshall Islands, the national airline of the Marshall Islands.
-
C.
CWM
CWM is an international committee of the International Mathematical Union dedicated to promoting and supporting the participation of women in mathematics worldwide.
-
D.
cwm
cwm is a lightweight, keyboard-centric stacking window manager for X11, known for its simplicity and inclusion as the default in OpenBSD.
-
E.
CUWMA
CUWMA is an academic organization or department associated with George Washington University, likely focused on a specialized area of research or study.
- 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_69d8e8d04d5c8190baa816986f2b1d1e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e60d833034819092a8414d5e0fc26e |
completed | April 20, 2026, 11:26 a.m. |
Created at: April 10, 2026, 1:32 p.m.