Triple
T3451283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vivaldi |
E72798
|
entity |
| Predicate | usesEngine |
P2092
|
FINISHED |
| Object | Blink |
E13758
|
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: Blink | Statement: [Vivaldi, usesEngine, Blink]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Blink Context triple: [Vivaldi, usesEngine, Blink]
-
A.
Blink
chosen
Blink is an open-source web browser engine developed primarily by Google and used in several major browsers to render web pages.
-
B.
Red Eye
Red Eye is a 2005 psychological thriller film in which Cillian Murphy plays a charming but menacing terrorist who coerces a hotel manager during a tense overnight flight.
-
C.
"Don't blink"
"Don't blink" is the iconic warning associated with the Weeping Angels in Doctor Who, urging characters to avoid blinking to escape these predatory creatures.
-
D.
BOLT
BOLT is the Bombay Stock Exchange’s proprietary electronic trading platform used to facilitate fast, automated securities trading in India.
-
E.
In the Blink of an Eye
In the Blink of an Eye is a widely acclaimed book on the art and philosophy of film editing, written by renowned editor and sound designer Walter Murch.
- 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_69ad85b12a908190a1d10a6b03b4f8ae |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adba7465248190947f9096e230e1c4 |
completed | March 8, 2026, 6:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4cdce42688190b6f33b39649fedd7 |
completed | March 14, 2026, 2:54 a.m. |
Created at: March 8, 2026, 3:16 p.m.