Triple
T32720343
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windows 10 October 2020 Update |
E836653
|
entity |
| Predicate | followsVersion |
P125022
|
FINISHED |
| Object | Windows 10 version 2004 |
—
|
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: Windows 10 version 2004 | Statement: [Windows 10 October 2020 Update, followsVersion, Windows 10 version 2004]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsVersion Context triple: [Windows 10 October 2020 Update, followsVersion, Windows 10 version 2004]
-
A.
followsReleaseStrategyOf
Indicates that one entity adopts or adheres to the same release strategy or release management approach as another entity.
-
B.
followsIn
chosen
Indicates that one entity comes after or succeeds another in a sequence, order, or progression.
-
C.
followsTo
Indicates that one entity moves or proceeds behind another entity toward a specific destination or target.
-
D.
follows
Indicates that one entity comes after, moves behind, or acts in accordance with another entity in time, space, or sequence.
-
E.
followsBetween
Indicates that one entity comes after or succeeds another entity within a specified context or sequence.
- 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_69f34935455881909088975d79460418 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fe2f078c24819082ba396b56f02808 |
completed | May 8, 2026, 6:44 p.m. |
| PD | Predicate disambiguation | batch_69fe228fe1988190baf3bb34897f3dbe |
completed | May 8, 2026, 5:51 p.m. |
Created at: May 1, 2026, 1:11 a.m.