Triple
T9484798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Garden Grill Restaurant |
E228730
|
entity |
| Predicate | rotationFeature |
P86397
|
FINISHED |
| Object | restaurant slowly rotates during meal |
—
|
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: restaurant slowly rotates during meal | Statement: [Garden Grill Restaurant, rotationFeature, restaurant slowly rotates during meal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rotationFeature Context triple: [Garden Grill Restaurant, rotationFeature, restaurant slowly rotates during meal]
-
A.
rotationProcess
chosen
Indicates a process in which something is turned or rotated around an axis or point over time.
-
B.
rotationType
Indicates the specific kind or mode of rotational movement or orientation applied in a given context.
-
C.
rotationPractice
Indicates that an entity engages in or is involved with practicing rotational movements or rotation-related skills.
-
D.
rotationSense
Indicates the direction or orientation in which an object or system rotates relative to a defined reference frame.
-
E.
rotationEffect
Indicates that one entity is rotated around a specified point or axis by a given angle, affecting its orientation relative to other entities.
- 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_69ca84730a5081908de282651019bf2f |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd804e278c8190b1f869158075cd52 |
completed | April 1, 2026, 8:30 p.m. |
| PD | Predicate disambiguation | batch_69cca561e6b0819090aa795f3c3a2083 |
completed | April 1, 2026, 4:56 a.m. |
Created at: March 30, 2026, 7:55 p.m.