Triple
T21102978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rosetta |
E519956
|
entity |
| Predicate | associatedWithThemeOfWork |
P56598
|
FINISHED |
| Object | psychological introspection |
—
|
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: psychological introspection | Statement: [Rosetta, associatedWithThemeOfWork, psychological introspection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithThemeOfWork Context triple: [Rosetta, associatedWithThemeOfWork, psychological introspection]
-
A.
associatedWithWorkTheme
chosen
Indicates a relationship where something is connected or related to a particular work theme or subject matter.
-
B.
associatedWithWorkOf
Indicates that one entity has a connection or involvement with the work, creation, or output produced by another entity.
-
C.
associatedWithAuthorTheme
Indicates a relationship where an author is linked to, or characterized by, a particular theme in their work or thought.
-
D.
associatedWork
Indicates that there exists a related or connected work (such as a publication, creative piece, or project) that is meaningfully linked to the subject.
-
E.
associatedWithAuthorWork
Indicates a relationship where an author is connected to a work they created, contributed to, or are otherwise credited for.
- 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_69e0b508d8dc81909be940dafe36c8f7 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e71b5ee8948190ac6e9e144d312c90 |
completed | April 21, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_69e5dbff56848190a03b350a9305c612 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:53 p.m.