Triple
T28220964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marguerite Gachet at the Piano |
E711453
|
entity |
| Predicate | hasPortrayedPerson |
P1507
|
FINISHED |
| Object | Marguerite Gachet |
—
|
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: Marguerite Gachet | Statement: [Marguerite Gachet at the Piano, hasPortrayedPerson, Marguerite Gachet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPortrayedPerson Context triple: [Marguerite Gachet at the Piano, hasPortrayedPerson, Marguerite Gachet]
-
A.
hasPortrayedPersonRole
Indicates that an entity has performed or held a specific role in portraying a particular person (e.g., in a film, play, or other representation).
-
B.
hasPortrayedRole
Indicates that an entity has performed or depicted a specific role or character, typically in a work such as a film, play, or television show.
-
C.
hasPortrayedPersonTitle
Indicates that a work or depiction features a portrayed person who holds or is associated with a specific title.
-
D.
portrayedBy
chosen
Indicates that one entity serves as the actor or performer who represents or plays the role of another entity in a work or medium.
-
E.
alsoPortrayedBy
Indicates that the same role or character is portrayed by an additional, different performer or actor.
- 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_69efb51dfb048190ada79b745c33b363 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69fcf1b3d9a08190850b388308656266 |
completed | May 7, 2026, 8:10 p.m. |
| PD | Predicate disambiguation | batch_69fcf0226d8c8190b23dceafb1794995 |
completed | May 7, 2026, 8:03 p.m. |
Created at: April 27, 2026, 10:46 p.m.