Triple
T17782447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | My Bed |
E443930
|
entity |
| Predicate | locationAfterSale |
P42649
|
FINISHED |
| Object | Tate Britain (long-term loan) |
—
|
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: Tate Britain (long-term loan) | Statement: [My Bed, locationAfterSale, Tate Britain (long-term loan)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationAfterSale Context triple: [My Bed, locationAfterSale, Tate Britain (long-term loan)]
-
A.
locationAfterConversion
Indicates the place or position an entity occupies after it has been transformed, converted, or changed from one state or form to another.
-
B.
locatedAfter
Indicates that one entity is positioned later than another along a defined sequence, order, or spatial/temporal axis.
-
C.
locationOfDelivery
Indicates the place or address where an item, service, or shipment is to be delivered.
-
D.
soldAfter
Indicates that one item was sold at a later time than another item.
-
E.
laterLocation
chosen
Indicates that an entity is located at a specified place at a later time than some reference time or earlier location.
- 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_69d8b9ef17708190bdf7e2adbf14ddc2 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4872260b881908e77096500451816 |
completed | April 19, 2026, 7:41 a.m. |
| PD | Predicate disambiguation | batch_69e3d8d8e538819084f1584426b41d5e |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:12 a.m.