Triple
T2105100
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windows 7 |
E37174
|
entity |
| Predicate | introducedFeature |
P513
|
FINISHED |
| Object | Aero Shake |
E193866
|
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: Aero Shake | Statement: [Windows 7, introducedFeature, Aero Shake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aero Shake Context triple: [Windows 7, introducedFeature, Aero Shake]
-
A.
Aero Shake
chosen
Aero Shake is a Windows desktop feature that lets you quickly minimize all other open windows by clicking and shaking the title bar of the active window.
-
B.
Avenol
Avenol is a French surname most notably borne by Joseph Avenol, a former Secretary-General of the League of Nations.
-
C.
Spontex
Spontex is a household cleaning products brand, best known for its sponges and related cleaning tools, owned by Newell Brands.
-
D.
Oxy
Oxy is the commonly used nickname for Occidental College, a private liberal arts college in Los Angeles, California.
-
E.
Olite
Olite is a historic town in northern Spain renowned for its well-preserved medieval architecture and the royal palace of the kings of Navarre.
- 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_69a8861828948190924aa30c08806b3a |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abbadcd4a081909d60b9b241950335 |
completed | March 7, 2026, 5:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae306bee8881908c62306fb1f6aea1 |
completed | March 9, 2026, 2:29 a.m. |
Created at: March 4, 2026, 7:43 p.m.