Triple
T35914114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rainbow Portrait |
E1038697
|
entity |
| Predicate | depictsHeaddress |
P193967
|
FINISHED |
| Object | ornate jeweled headdress |
—
|
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: ornate jeweled headdress | Statement: [Rainbow Portrait, depictsHeaddress, ornate jeweled headdress]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictsHeaddress Context triple: [Rainbow Portrait, depictsHeaddress, ornate jeweled headdress]
-
A.
obverseHeaddressType
Indicates the type or style of headdress depicted on the obverse (front) side of an object, typically a coin or medal.
-
B.
traditionalHeaddress
Indicates that an entity wears or is associated with a culturally traditional headdress as part of customary or ceremonial attire.
-
C.
skullOrnamentation
Indicates that an entity has decorative or structural features specifically adorning or modifying the skull.
-
D.
depictsName
Indicates that something visually represents or portrays the name of an entity.
-
E.
depicts costume
Indicates that one entity visually represents or portrays the clothing or outfit associated with another entity.
- 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_69f76e2259608190bf6788a132e0d139 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fd5bf69acc819092a01e4259785dc3 |
completed | May 8, 2026, 3:43 a.m. |
| PD | Predicate disambiguation | batch_69fd59b3f4ac8190a7f9dd3142da6e09 |
completed | May 8, 2026, 3:34 a.m. |
| PDg | Predicate description generation | batch_69fd5bf49288819098a12202411cba4f |
completed | May 8, 2026, 3:43 a.m. |
Created at: May 3, 2026, 4:07 p.m.