Triple
T1313499
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Benois Madonna |
E28046
|
entity |
| Predicate | emotionDepicted |
P23736
|
FINISHED |
| Object | maternal tenderness |
—
|
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: maternal tenderness | Statement: [Benois Madonna, emotionDepicted, maternal tenderness]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: emotionDepicted Context triple: [Benois Madonna, emotionDepicted, maternal tenderness]
-
A.
viewOnEmotion
Indicates a relationship where one entity holds a particular emotional perspective, reaction, or attitude toward another entity or situation.
-
B.
faceExpression
chosen
Indicates the specific facial expression an entity is displaying, capturing its visible emotional or expressive state.
-
C.
upset
Indicates that one entity causes another to feel distressed, unhappy, or emotionally disturbed.
-
D.
aspect
Indicates a specific temporal phase or manner in which an action, event, or state unfolds or is viewed (e.g., ongoing, completed, habitual).
-
E.
sentience
Indicates that an entity possesses the capacity for subjective experience, awareness, or feeling.
- 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_69a498532c3481909223b74af2e578df |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c1585d3081909ca0221c23de63ba |
completed | March 1, 2026, 10:44 p.m. |
| PD | Predicate disambiguation | batch_69a4beebcb348190964bd7215811942c |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:55 p.m.