Triple
T28027017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Microsoft Office Home & Business 2013 RT |
E708151
|
entity |
| Predicate | preInstalledOn |
P8873
|
FINISHED |
| Object | Surface 2 |
—
|
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: Surface 2 | Statement: [Microsoft Office Home & Business 2013 RT, preInstalledOn, Surface 2]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preInstalledOn Context triple: [Microsoft Office Home & Business 2013 RT, preInstalledOn, Surface 2]
-
A.
preinstalledOn
chosen
Indicates that a software or component comes already installed and ready to use on a particular device or system before the user receives it.
-
B.
installedFor
Indicates that something has been set up or put in place to be used by or on behalf of a particular entity.
-
C.
installedAt
Indicates that something has been set up, placed, or put into operation at a specific location or site.
-
D.
installedPower
Indicates the total nominal power capacity that has been set up or equipped for use in a system, device, or facility.
-
E.
installedInstrument
Indicates that one entity has placed or set up another entity as an instrument or device for use in a particular context or system.
- 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_69ef9b6bdd9c8190bb3a574a03774ad1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f63c6ef4348190821f991c682a6894 |
completed | May 2, 2026, 6:03 p.m. |
| PD | Predicate disambiguation | batch_69f63710d17c819084cfe96e6df334fd |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 8:13 p.m.