Triple
T14387989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GSMA |
E356772
|
entity |
| Predicate | focusesOn |
P31
|
FINISHED |
| Object | eSIM |
E72118
|
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: eSIM | Statement: [GSMA, focusesOn, eSIM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: eSIM Context triple: [GSMA, focusesOn, eSIM]
-
A.
eSIM
chosen
eSIM is an embedded, programmable SIM technology built into devices that lets users activate and switch mobile carriers digitally without needing a physical SIM card.
-
B.
iSIM
iSIM is an integrated SIM technology that embeds subscriber identity functionality directly into a device’s main chipset, offering a more compact and power-efficient alternative to traditional SIM and eSIM solutions.
-
C.
USIM
USIM is a Malaysian public university that integrates Islamic values with modern scientific and professional education.
-
D.
USIM
USIM (Universal Subscriber Identity Module) is a smart card application used in 3G and later mobile networks to securely store subscriber credentials and enable authentication and access to network services.
-
E.
SIM30
SIM30 is a New York City express bus route that provides commuter service between Staten Island and Manhattan.
- 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_69d827927c988190ad98bb0360981783 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de90283b9c8190b50d30ad58bfe085 |
completed | April 14, 2026, 7:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd551623608190ba1de09b423cc5e1 |
completed | May 8, 2026, 3:14 a.m. |
Created at: April 10, 2026, 1:16 a.m.