Triple
T30556837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arnold Machin |
E777720
|
entity |
| Predicate | workUsedOn |
P42407
|
FINISHED |
| Object | United Kingdom coins |
—
|
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: United Kingdom coins | Statement: [Arnold Machin, workUsedOn, United Kingdom coins]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workUsedOn Context triple: [Arnold Machin, workUsedOn, United Kingdom coins]
-
A.
workUsedFor
Indicates that a particular work (such as a document, artwork, or dataset) is employed or utilized for a specific purpose, task, or function.
-
B.
workUsedAs
chosen
Indicates that one work is employed or utilized in the creation, performance, or presentation of another work.
-
C.
usedInWorkBy
Indicates that something (such as a method, material, or concept) is employed or incorporated within a work created by a particular agent or author.
-
D.
usedInWork
Indicates that something (such as a concept, method, material, or component) is employed or applied within a particular work, project, or creation.
-
E.
worksTo
Indicates that one entity performs work or exerts effort in order to achieve, support, or contribute to another entity or outcome.
- 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_69f2249ed41c8190b175170ecfd6e1c5 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f688d564a88190b78eebeb163b76f6 |
completed | May 2, 2026, 11:29 p.m. |
| PD | Predicate disambiguation | batch_69f67e42d6688190b60e91d2c388c555 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 8:20 p.m.