Triple
T37661513
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | End Midlands |
E937726
|
entity |
| Predicate | hasBedBehavior |
P100255
|
FINISHED |
| Object | beds explode when used |
—
|
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: beds explode when used | Statement: [End Midlands, hasBedBehavior, beds explode when used]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBedBehavior Context triple: [End Midlands, hasBedBehavior, beds explode when used]
-
A.
hasBedType
Indicates that an entity (such as a room or accommodation) is associated with a specific type or configuration of bed.
-
B.
bedBehavior
chosen
Indicates how an entity typically acts, functions, or is used in relation to a bed.
-
C.
hasBedMaterial
Indicates that one entity has, contains, or is characterized by a particular bed material (e.g., the substance forming the base or bedding of that entity).
-
D.
beds
Indicates that one entity provides or designates a place for another entity to sleep or rest.
-
E.
cargoBedType
Indicates the specific type or configuration of a vehicle’s cargo bed associated with an entity.
- 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd592e48cc81909d754cc6c4bd99ae |
completed | May 8, 2026, 3:31 a.m. |
| PD | Predicate disambiguation | batch_69fd58b7f9b881909dc099b28d567784 |
completed | May 8, 2026, 3:30 a.m. |
Created at: May 3, 2026, 4:18 p.m.