Triple
T16810814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adrian’s Restaurant |
E408601
|
entity |
| Predicate | onScreenUse |
P87539
|
FINISHED |
| Object | setting for conversations about boxing |
—
|
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: setting for conversations about boxing | Statement: [Adrian’s Restaurant, onScreenUse, setting for conversations about boxing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onScreenUse Context triple: [Adrian’s Restaurant, onScreenUse, setting for conversations about boxing]
-
A.
operatesWhenScreenOn
Indicates that the action or process occurs only while the screen is turned on.
-
B.
hasOnscreenFunction
chosen
Indicates that an entity serves a particular role or performs a specific function when it appears on screen.
-
C.
hasScreen
Indicates that an entity is equipped with or includes a screen or display component.
-
D.
usedOn
Indicates that one entity is applied to, operated on, or otherwise utilized in relation to another entity.
-
E.
usesSurface
Indicates that one entity employs or interacts with another entity as a surface or platform for its action or function.
- 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_69d88393905081908d00a86b99996ac8 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3b2cf680c8190bcd640570c524918 |
completed | April 18, 2026, 4:35 p.m. |
| PD | Predicate disambiguation | batch_69e32b814b188190aee525f8779203cd |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:23 a.m.