Triple
T19984577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Death Eaters |
E493902
|
entity |
| Predicate | symbolDepicts |
P8270
|
FINISHED |
| Object | skull with a serpent tongue |
—
|
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: skull with a serpent tongue | Statement: [Death Eaters, symbolDepicts, skull with a serpent tongue]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: symbolDepicts Context triple: [Death Eaters, symbolDepicts, skull with a serpent tongue]
-
A.
imageDepictedIn
Indicates that a particular image is shown, represented, or included within another resource or context.
-
B.
intendedToDepict
Indicates that one entity was purposefully created or selected in order to visually represent or portray another entity.
-
C.
iconographyType
Indicates the specific kind or category of visual symbolism or imagery used to represent something.
-
D.
symbolDescription
Indicates that a symbol is associated with or defined by a particular descriptive explanation or meaning.
-
E.
iconographyFeature
chosen
Indicates a visual element or motif that appears as a distinct feature within a work’s iconography.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65d157d088190af861608936e59b7 |
completed | April 20, 2026, 5:06 p.m. |
| PD | Predicate disambiguation | batch_69e537fae79c81909eae39500766d0b6 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 11, 2026, 3:29 p.m.