Triple
T28617780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windows 10 |
E724310
|
entity |
| Predicate | edition |
P4629
|
FINISHED |
| Object |
Windows 10 Home
Windows 10 Home is the consumer-focused edition of Microsoft's Windows 10 operating system, designed for use on personal PCs, laptops, and tablets with core features like the Start menu, Cortana, and Microsoft Store apps.
|
E38676
|
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: Windows 10 Home | Statement: [Windows 10, edition, Windows 10 Home]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Windows 10 Home Triple: [Windows 10, edition, Windows 10 Home]
Generated description
Windows 10 Home is the consumer-focused edition of Microsoft's Windows 10 operating system, designed for use on personal PCs, laptops, and tablets with core features like the Start menu, Cortana, and Microsoft Store apps.
Provenance (5 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_69f01d816d7c8190a1fe27e3434041dc |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f65246b3988190929e550617990982 |
completed | May 2, 2026, 7:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a1cb70f7b008190b012a9e6dfd76d3c |
completed | May 31, 2026, 10:32 p.m. |
| NEDg | Description generation | batch_6a1cba6346dc8190a7e92e045ccb035c |
completed | May 31, 2026, 10:46 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a1cbaf9b0988190bab3dc98fa1d257b |
completed | May 31, 2026, 10:49 p.m. |
Created at: April 28, 2026, 4:32 a.m.