Triple
T28455629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dumfries House |
E716703
|
entity |
| Predicate | hasFurnitureMaker |
P118614
|
FINISHED |
| Object | Thomas Chippendale |
—
|
NE NERFINISHED |
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: Thomas Chippendale | Statement: [Dumfries House, hasFurnitureMaker, Thomas Chippendale]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFurnitureMaker Context triple: [Dumfries House, hasFurnitureMaker, Thomas Chippendale]
-
A.
hasCraftsman
Indicates that one entity serves as the craftsman, maker, or artisan responsible for creating, building, or crafting another entity.
-
B.
makerOf
Indicates that one entity is the creator, producer, or manufacturer of another entity.
-
C.
hasSculptor
Indicates that one entity serves as the sculptor (creator of a sculpture) of another entity.
-
D.
eraOfFurnishings
Indicates the historical time period or style from which a set of furnishings originates or to which it belongs.
-
E.
associatedCraftsmen
chosen
Indicates that there is a relationship linking an entity to one or more craftsmen who are connected to it through work, creation, or service.
- 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_69efd6b76f8c8190a7ba908aca280942 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 1:54 a.m.