Triple
T29368884
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Girl in the Kremlin |
E744797
|
entity |
| Predicate | featuresFictionalDepictionOf |
P197532
|
FINISHED |
| Object | Joseph Stalin |
—
|
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: Joseph Stalin | Statement: [The Girl in the Kremlin, featuresFictionalDepictionOf, Joseph Stalin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresFictionalDepictionOf Context triple: [The Girl in the Kremlin, featuresFictionalDepictionOf, Joseph Stalin]
-
A.
hasFictionalDepictions
Indicates that an entity is represented or portrayed in one or more fictional works or narratives.
-
B.
fictionalCharacterDepicted
Indicates that one entity is a fictional character and the other is a work or medium in which that character is visually or narratively depicted.
-
C.
fictionalPortrayalOf
Indicates that one entity is a fictional representation, depiction, or dramatization of another entity.
-
D.
depictionBasedOn
Indicates that one depiction is created using another work, image, or representation as its source or reference.
-
E.
fictionalPortrayalSubject
chosen
Indicates that one entity is the subject or topic being portrayed, depicted, or represented in a fictional work by 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_69f0a79ba954819094597628112c6091 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69ff65987ff88190b09be64f7c0e1da9 |
completed | May 9, 2026, 4:49 p.m. |
| PD | Predicate disambiguation | batch_69ff6525b0548190bef7a9f009e00bb8 |
completed | May 9, 2026, 4:47 p.m. |
Created at: April 28, 2026, 2:25 p.m.