Triple
T8509384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fresh Widow |
E201413
|
entity |
| Predicate | subverts |
P4938
|
FINISHED |
| Object | traditional painting conventions |
—
|
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: traditional painting conventions | Statement: [Fresh Widow, subverts, traditional painting conventions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subverts Context triple: [Fresh Widow, subverts, traditional painting conventions]
-
A.
corrupts
Indicates that one entity causes another entity, system, or process to become morally, functionally, or structurally degraded or impaired.
-
B.
negates
Indicates that one entity denies, contradicts, or renders false the assertion, state, or effect expressed by another.
-
C.
inhibits
Indicates that one entity prevents, restrains, or reduces the activity, effect, or occurrence of another entity.
-
D.
undermined
chosen
Indicates that one entity has weakened, subverted, or reduced the effectiveness, authority, or stability of another entity or its position.
-
E.
correctsAberration
Indicates that one entity counteracts, fixes, or compensates for an error, flaw, or deviation present in 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_69ca8320e5748190ac2c585a0bba8193 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe5e0cb1881909d1ff6ee9b3a65cc |
completed | March 31, 2026, 3:18 p.m. |
| PD | Predicate disambiguation | batch_69cbd10cfd208190a519049fad32c508 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:15 p.m.