Triple
T7981937
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portrait of a Nobleman with his Hand on his Chest |
E185589
|
entity |
| Predicate | depictsAccessory |
P31021
|
FINISHED |
| Object | sword hilt |
—
|
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: sword hilt | Statement: [Portrait of a Nobleman with his Hand on his Chest, depictsAccessory, sword hilt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictsAccessory Context triple: [Portrait of a Nobleman with his Hand on his Chest, depictsAccessory, sword hilt]
-
A.
accessory
chosen
Indicates that one entity serves as a supplementary or supporting item to another, often enhancing its function, use, or appearance.
-
B.
depictsAttribute
Indicates that one entity visually represents or illustrates a specific attribute or characteristic of another entity.
-
C.
depictsWeapon
Indicates that one entity visually represents or shows a weapon associated with another entity.
-
D.
depicts
Indicates that one entity visually represents, portrays, or shows another entity.
-
E.
depictsTool
Indicates that one entity visually represents or shows a tool in some form of depiction (e.g., an image, illustration, or artwork).
- 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_69ca829a2cfc819083d591d58ec04075 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c28cb108190bca697600bbbf53b |
completed | March 31, 2026, 3:14 a.m. |
| PD | Predicate disambiguation | batch_69cb048009a08190b4c577208a9f8f76 |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:15 p.m.