Triple
T19452216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sonos, Inc. |
E486639
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Trung Mai |
—
|
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: Trung Mai | Statement: [Sonos, Inc., foundedBy, Trung Mai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Trung Mai Context triple: [Sonos, Inc., foundedBy, Trung Mai]
-
A.
Trung Mai
chosen
Trung Mai is an entrepreneur best known as a co-founder of the audio technology company Sonos.
-
B.
Trung Mai
Trung Mai is an entrepreneur and business leader best known as the founder of the technology company Rincon Networks.
-
C.
Chongxi
Chongxi is the given name of Bai Chongxi, a prominent Chinese Muslim general and political figure of the Republic of China.
-
D.
Dong Dang
Dong Dang is a border town in northern Vietnam that serves as a key railway gateway for international train connections between Vietnam and China.
-
E.
Zhonghe
Zhonghe was the reign era title used by Emperor Xizong during a late period of the Tang dynasty in China.
- 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_69d8e8d86d608190bd199a98d0297f27 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63392aab08190aab09b7c356e5b10 |
completed | April 20, 2026, 2:09 p.m. |
Created at: April 10, 2026, 1:38 p.m.