Triple
T21983225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WebBrowser |
E542891
|
entity |
| Predicate | userInteractsVia |
P66544
|
FINISHED |
| Object | mouse |
—
|
LITERAL 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: mouse | Statement: [WebBrowser, userInteractsVia, mouse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: userInteractsVia Context triple: [WebBrowser, userInteractsVia, mouse]
-
A.
usedInteractionType
Indicates the specific type or category of interaction that was used between the related entities.
-
B.
interactionMechanism
chosen
Indicates the process or means by which one entity affects, influences, or interacts with another.
-
C.
userInterface
Indicates a relationship where one entity serves as the interface or interaction layer through which a user engages with another system, service, or resource.
-
D.
userInteractionModel
Indicates how a user is expected to interact with a system, defining the style, rules, or pattern of those interactions.
-
E.
interactionWithHumans
Indicates a relationship where an entity engages in some form of contact, communication, or mutual influence with humans.
- 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_69e0c48136b081908831fa907cc02e18 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1270629588190aea32fbe630e4cba |
completed | April 28, 2026, 9:30 p.m. |
| PD | Predicate disambiguation | batch_69e6f6154e408190acc5b2c278acaff4 |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:04 p.m.