Triple
T19586772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bitwarden |
E490125
|
entity |
| Predicate | supportsBrowser |
P5090
|
FINISHED |
| Object | Google Chrome |
—
|
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: Google Chrome | Statement: [Bitwarden, supportsBrowser, Google Chrome]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Google Chrome Context triple: [Bitwarden, supportsBrowser, Google Chrome]
-
A.
Google Chrome
chosen
Google Chrome is a widely used cross-platform web browser developed by Google, known for its speed, simplicity, and integration with Google services.
-
B.
Chrome
Chrome is a track featured on the album "Rain."
-
C.
Chrome
Chrome is an unincorporated rural community located in Glenn County, California.
-
D.
Yandex Browser
Yandex Browser is a web browser developed by the Russian company Yandex that emphasizes speed, security, and integration with Yandex’s online services.
-
E.
Chromium web browser
Chromium web browser is an open-source, multi-platform web browser that serves as the foundation for Google Chrome and many other Chromium-based browsers.
- 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_69d8e8dd9374819098e36349b3211663 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e640523d10819091320a61456f6437 |
completed | April 20, 2026, 3:03 p.m. |
Created at: April 10, 2026, 1:42 p.m.