Triple
T15018691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portrait of Talleyrand |
E378024
|
entity |
| Predicate | depictsSocialRole |
P17608
|
FINISHED |
| Object | statesman |
—
|
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: statesman | Statement: [Portrait of Talleyrand, depictsSocialRole, statesman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictsSocialRole Context triple: [Portrait of Talleyrand, depictsSocialRole, statesman]
-
A.
depictsPersonRole
chosen
Indicates that an image or representation shows a person in a specific role, function, or capacity.
-
B.
depictsPerson
Indicates that one entity visually represents or portrays a specific person.
-
C.
depictsAffiliation
Indicates that one entity visually represents or portrays the association, membership, or allegiance of another entity to a group, organization, or cause.
-
D.
designedRole
Indicates that one entity has been created, configured, or intended to serve a particular function, purpose, or role in relation to another entity.
-
E.
representedRole
Indicates that one entity serves as a stand-in, proxy, or representative performing a role on behalf of another 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded76445988190984b57de66e00c4a |
completed | April 15, 2026, 12:10 a.m. |
| PD | Predicate disambiguation | batch_69de9a67cbc481909c19c2de57de4eb7 |
completed | April 14, 2026, 7:50 p.m. |
Created at: April 10, 2026, 2:56 a.m.