Triple
T18404937
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rogers Communications Inc. |
E450099
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object | Chatr |
—
|
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: Chatr | Statement: [Rogers Communications Inc., brand, Chatr]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chatr Context triple: [Rogers Communications Inc., brand, Chatr]
-
A.
Chatr Mobile
chosen
Chatr Mobile is a Canadian prepaid wireless service provider offering low-cost, no-contract mobile plans, primarily targeting budget-conscious and urban customers.
-
B.
Boingo
Boingo is the 1994 self-titled studio album by American new wave band Oingo Boingo, marking a stylistic shift toward a more alternative rock sound.
-
C.
Beeline
Beeline is a command-line client for Apache Hive that allows users to connect to HiveServer2 and execute SQL queries against Hive data warehouses.
-
D.
Gogo
Gogo is an in-flight internet service provider known for supplying Wi-Fi connectivity on commercial airlines.
-
E.
Gogo
Gogo is a diminutive form of the given name Georgi, commonly used as an affectionate nickname.
- 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_69d8b9fab8a8819086a9ddc0871715e0 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e51956b8c88190b863e66871825014 |
completed | April 19, 2026, 6:05 p.m. |
Created at: April 10, 2026, 10:46 a.m.