Triple
T14480199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue Dress A |
E359081
|
entity |
| Predicate | hasVisualProperty |
P99801
|
FINISHED |
| Object | blue appearance |
—
|
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: blue appearance | Statement: [Blue Dress A, hasVisualProperty, blue appearance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVisualProperty Context triple: [Blue Dress A, hasVisualProperty, blue appearance]
-
A.
hasVisualCharacter
chosen
Indicates that one entity possesses or exhibits a particular visual appearance, style, or graphical characteristic defined by another entity.
-
B.
hasVisualIndicator
Indicates that an entity is associated with some form of visual cue or marker that signals its status, condition, or presence.
-
C.
hasVisibilityCharacteristic
Indicates that one entity possesses a specific property or quality related to how visible or observable it is.
-
D.
hasVisualFocus
Indicates that one entity is currently directing its visual attention or gaze toward another entity.
-
E.
hasVisibility
Indicates that one entity can perceive, view, or access another entity or its information under certain conditions.
- 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_69d827966698819082e140837737501d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de924a576c819098351efabdb779b1 |
completed | April 14, 2026, 7:15 p.m. |
| PD | Predicate disambiguation | batch_69de5c487b4c819097803e58dca628a5 |
completed | April 14, 2026, 3:24 p.m. |
Created at: April 10, 2026, 1:20 a.m.