Triple
T30267029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Chocolate Soldier |
E769676
|
entity |
| Predicate | sourceWorkPlaywright |
P170712
|
FINISHED |
| Object | George Bernard Shaw |
—
|
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: George Bernard Shaw | Statement: [The Chocolate Soldier, sourceWorkPlaywright, George Bernard Shaw]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceWorkPlaywright Context triple: [The Chocolate Soldier, sourceWorkPlaywright, George Bernard Shaw]
-
A.
laterPlaywright
Indicates that one person became a playwright at a later time than another person.
-
B.
playwrightOfSourcePlay
chosen
Indicates that one entity is the playwright who authored the original source play from which another work is derived.
-
C.
hasPlaywright
Indicates that one entity is the playwright who wrote or created the play associated with another entity.
-
D.
activeAsPlaywrightFrom
Indicates the time period during which an entity was actively working in the role of a playwright.
-
E.
sourceWorkSection
Indicates that one entity is a specific section or part extracted from a larger source work.
- 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_69f224856d9881908c7f0dd64f059672 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6b903538481909cffcb6cc1cc0e70 |
completed | May 3, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69f6b626120c819097c9ad04487570d7 |
completed | May 3, 2026, 2:42 a.m. |
Created at: April 29, 2026, 7:43 p.m.