Triple
T5443510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sideways |
E122192
|
entity |
| Predicate | oftenPortrayedAs |
P18297
|
FINISHED |
| Object | double agent |
—
|
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: double agent | Statement: [Sideways, oftenPortrayedAs, double agent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenPortrayedAs Context triple: [Sideways, oftenPortrayedAs, double agent]
-
A.
oftenDepictedAs
chosen
Indicates that one entity is frequently represented or portrayed in the form, appearance, or symbolism of another entity.
-
B.
wasPortrayedAs
Indicates that one entity has been depicted or represented in the form or role of another entity, typically within some medium or context.
-
C.
portrayedAsFrom
Indicates that one entity is depicted or represented as originating from, or belonging to, the place or source specified by another entity.
-
D.
portrayalLedTo
Indicates that one entity’s portrayal of another caused or significantly contributed to a subsequent outcome, reaction, or state involving that other entity.
-
E.
workOftenDepicts
Indicates that one entity’s work frequently portrays, represents, or includes the other entity as a subject or theme.
- 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_69bd4640f52c81909e653ec361f66d76 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd922f66bc8190b7d47fd68d2fcf2e |
completed | March 20, 2026, 6:30 p.m. |
| PD | Predicate disambiguation | batch_69bd919aeb048190b786f814177d6cd9 |
completed | March 20, 2026, 6:27 p.m. |
Created at: March 20, 2026, 2:07 p.m.