Triple
T21585845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portrait of a Young Man (National Gallery, London) |
E532647
|
entity |
| Predicate | sitterIdentity |
P119779
|
FINISHED |
| Object | unidentified |
—
|
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: unidentified | Statement: [Portrait of a Young Man (National Gallery, London), sitterIdentity, unidentified]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sitterIdentity Context triple: [Portrait of a Young Man (National Gallery, London), sitterIdentity, unidentified]
-
A.
sitterNationality
Indicates the national identity or citizenship of the person who is sitting for a portrait or being depicted.
-
B.
sitterName
chosen
Indicates the name associated with a person who is acting as a sitter in the described context.
-
C.
sitter
Indicates that one entity is serving as a caretaker or guardian, typically watching over or looking after another entity.
-
D.
sitterOf
Indicates that one entity serves as a caretaker or babysitter responsible for looking after another entity.
-
E.
sitterIn
Indicates that one entity is acting as a sitter (e.g., babysitter, pet sitter, house sitter) for another entity or at a particular place.
- 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_69e0c46251648190876f0427cf2d321b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eeeb60032881908dd35ac76392ad07 |
completed | April 27, 2026, 4:51 a.m. |
| PD | Predicate disambiguation | batch_69e632109d048190b4ac3f14fe48d1a0 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:31 p.m.