Triple
T37820594
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sir Gawain’s shield |
E942901
|
entity |
| Predicate | hasReverseImage |
P204409
|
FINISHED |
| Object | image of the Virgin Mary |
—
|
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: image of the Virgin Mary | Statement: [Sir Gawain’s shield, hasReverseImage, image of the Virgin Mary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReverseImage Context triple: [Sir Gawain’s shield, hasReverseImage, image of the Virgin Mary]
-
A.
hasReverse
Indicates that one entity serves as the inverse or opposite counterpart of another entity in a given relationship or operation.
-
B.
hasReverseFeature
Indicates that one entity possesses a feature that functions in the opposite or reverse manner of another related feature.
-
C.
inverseImage
Indicates the mapping from a set of outputs back to all inputs that are related to those outputs under a given function or relation.
-
D.
hasImageFeature
Indicates that an entity is associated with a specific visual characteristic or attribute extracted from an image.
-
E.
hasImageRole
Indicates that an image is associated with an entity in a specific functional or contextual role (e.g., thumbnail, icon, illustration).
- F. None of above. chosen
Provenance (4 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_69f76ee987588190906506e759be5db3 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037cae084081909004d77514c5f286 |
completed | May 12, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_6a037a1772e48190ba738c6d11b321e2 |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c84ecbc81908232e5215355f43b |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:19 p.m.