Triple
T19669517
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | T-Com |
E472295
|
entity |
| Predicate | technologyUsed |
P1485
|
FINISHED |
| Object | GSM |
—
|
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: GSM | Statement: [T-Com, technologyUsed, GSM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GSM Context triple: [T-Com, technologyUsed, GSM]
-
A.
GSM
chosen
GSM is a second-generation (2G) digital mobile communication standard that became the global foundation for cellular voice and basic data services.
-
B.
GSM
GSM is the common abbreviation for Great St Mary’s Church, the historic University Church located in the center of Cambridge, England.
-
C.
GSM
GSM is the three-letter IATA airport code assigned to Qeshm International Airport in Iran.
-
D.
GSM
GSM is a classic Onitsuka Tiger sneaker model inspired by vintage tennis shoes, known for its minimalist design and retro athletic style.
-
E.
GPRS
GPRS (General Packet Radio Service) is a mobile data standard that enables packet-switched internet and multimedia services over 2G and 3G cellular networks.
- 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_69d8e514f2e08190ba70a4449519d218 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6416ad1b481908d2890d8c21aac5c |
completed | April 20, 2026, 3:08 p.m. |
Created at: April 10, 2026, 1:45 p.m.