Triple
T27750380
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Microsoft Windows games |
E702098
|
entity |
| Predicate | publisherOfPlatform |
P24639
|
FINISHED |
| Object | Microsoft |
—
|
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: Microsoft | Statement: [Microsoft Windows games, publisherOfPlatform, Microsoft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publisherOfPlatform Context triple: [Microsoft Windows games, publisherOfPlatform, Microsoft]
-
A.
publishingPlatform
chosen
Indicates that one entity serves as the medium or service through which another entity is published or made publicly available.
-
B.
parentPlatformCompany
Indicates that one company serves as the overarching or owning platform company for another company within a corporate or business structure.
-
C.
publisherType
Indicates the classification or category of a publisher in relation to a published work or entity.
-
D.
publisherOfTextVersion
Indicates that an entity serves as the publisher responsible for a particular text version of a work.
-
E.
targetPlatformManufacturer
Indicates that one entity is the manufacturer or producer of the platform targeted or used by another entity.
- F. None of above.
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_69ef6a53c7388190899baa6daf42301c |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f7aa699d68819081ed363931894ab3 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8cec6d48190bebfa884b2f938c0 |
completed | May 3, 2026, 7:58 p.m. |
Created at: April 27, 2026, 4:19 p.m.