Triple
T31445410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brava Centauri |
E802172
|
entity |
| Predicate | platformOfWorkItAppearsIn |
P19094
|
FINISHED |
| Object | Microsoft Windows |
—
|
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 Windows | Statement: [Brava Centauri, platformOfWorkItAppearsIn, Microsoft Windows]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: platformOfWorkItAppearsIn Context triple: [Brava Centauri, platformOfWorkItAppearsIn, Microsoft Windows]
-
A.
platformOfWorkAppearingIn
chosen
Indicates the platform or medium on which a given work is presented, published, or made available.
-
B.
platformAppearsOn
Indicates that a particular platform is present, visible, or available within or on another specified context, medium, or environment.
-
C.
platformShowcased
Indicates that a platform is prominently presented or highlighted, typically to draw attention to its features, capabilities, or offerings.
-
D.
platformTypeWorkedOn
Indicates the type of platform on which an entity (typically a person or system) has performed work or carried out activities.
-
E.
worksOnPlatform
Indicates that an entity performs its functions, operations, or activities using or within a specified platform.
- 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_69f348c5a6bc819092a557e95438976f |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6c8159edc8190b1c87015e0c820e8 |
completed | May 3, 2026, 3:59 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f42fbc8190a06eb1044c9e6094 |
completed | May 3, 2026, 3:41 a.m. |
Created at: April 30, 2026, 9:09 p.m.