Triple
T11291746
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | British Rail Class 387 |
E267340
|
entity |
| Predicate | safetySystem |
P840
|
FINISHED |
| Object | GSM-R |
E273829
|
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: GSM-R | Statement: [British Rail Class 387, safetySystem, GSM-R]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GSM-R Context triple: [British Rail Class 387, safetySystem, GSM-R]
-
A.
GSM-R
chosen
GSM-R is a digital radio communication system used across European railways to provide secure voice and data links between trains and railway control centers.
-
B.
GSM
GSM is the three-letter IATA airport code assigned to Qeshm International Airport in Iran.
-
C.
GSM
GSM is a second-generation (2G) digital mobile communication standard that became the global foundation for cellular voice and basic data services.
-
D.
GSM
GSM is the common abbreviation for Great St Mary’s Church, the historic University Church located in the center of Cambridge, England.
-
E.
GSM
GSM is a classic Onitsuka Tiger sneaker model inspired by vintage tennis shoes, known for its minimalist design and retro athletic style.
- 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_69d6aac993a08190a6f36445ebaf9a43 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e989fdac81909a4a75f1f68b55c6 |
completed | April 9, 2026, 6:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4f4a57d6881909a1e65744111ad8b |
completed | April 19, 2026, 3:28 p.m. |
Created at: April 8, 2026, 9:32 p.m.