Triple
T29011458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apple menu |
E736574
|
entity |
| Predicate | locationOnScreen |
P15688
|
FINISHED |
| Object | top-left corner of the menu bar |
—
|
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: top-left corner of the menu bar | Statement: [Apple menu, locationOnScreen, top-left corner of the menu bar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationOnScreen Context triple: [Apple menu, locationOnScreen, top-left corner of the menu bar]
-
A.
hasScreenLocation
Indicates that an entity is associated with a specific position or region on a screen or display surface.
-
B.
locationInSystem
Indicates that one entity is situated within or belongs to the spatial or organizational bounds of a particular system.
-
C.
locationPresented
Indicates that a specific location is presented or shown to an entity (such as a user or system) within a given context.
-
D.
uiLocation
chosen
Indicates the on-screen position or placement of a user interface element within a UI layout or display.
-
E.
locationOnDevice
Indicates that one entity is stored or situated on a particular device.
- 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_69f077eb81e88190ad9ff62cbb9f555e |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69ffe01c9d3c819084c256bb3c81c0dc |
completed | May 10, 2026, 1:32 a.m. |
| PD | Predicate disambiguation | batch_69ffdfcc78b08190aa4493f13d62a531 |
completed | May 10, 2026, 1:30 a.m. |
Created at: April 28, 2026, 9:42 a.m.