Triple
T2396353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mac |
E47659
|
entity |
| Predicate | supports |
P516
|
FINISHED |
| Object | Handoff |
E41895
|
NE 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: Handoff | Statement: [Mac, supports, Handoff]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Handoff Context triple: [Mac, supports, Handoff]
-
A.
Handoff
chosen
Handoff is an Apple continuity feature that lets users start an activity on one Apple device and seamlessly continue it on another, such as moving from an iPhone to a Mac.
-
B.
Midnight Office
Midnight Office is a Christian liturgical service of nighttime prayer, traditionally observed around midnight as part of the daily cycle of worship.
-
C.
Hands on the Wheel
"Hands on the Wheel" is a country song featured on Willie Nelson’s landmark concept album *Red Headed Stranger*.
-
D.
Heed
Heed is the fiercely loyal yet conflicted protagonist of Toni Morrison’s novel "Love," whose lifelong bond and rivalry with her friend Christine drive much of the story’s emotional and thematic tension.
-
E.
Gatekeeper
Gatekeeper is a macOS security feature that helps protect users by allowing only trusted software to run on the system.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a88a1c450c81909f61abb8b6863885 |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abc8c4a8bc819086892a75caac0207 |
completed | March 7, 2026, 6:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aeb3de3d548190b3eda939fa5f72b3 |
completed | March 9, 2026, 11:49 a.m. |
Created at: March 4, 2026, 7:57 p.m.