Triple
T15385214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dark-Light Device |
E367898
|
entity |
| Predicate | visualCue |
P29429
|
FINISHED |
| Object | revealed objects glow |
—
|
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: revealed objects glow | Statement: [Dark-Light Device, visualCue, revealed objects glow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visualCue Context triple: [Dark-Light Device, visualCue, revealed objects glow]
-
A.
visualCompanion
Indicates that one entity serves as a visual counterpart, partner, or accompanying element to another in a visual context.
-
B.
visualCenterpiece
Indicates that one entity serves as the primary visual focus or dominant visual element in relation to another entity.
-
C.
visualizedIn
Indicates that something is represented or depicted within a particular visual medium, view, or visualization.
-
D.
visionOrSign
Indicates a relationship where something is perceived or presented as a vision, sign, or symbolic manifestation, often conveying a message, omen, or divine indication.
-
E.
visualElements
chosen
Indicates that one entity contains, uses, or is characterized by specific visual components or graphical features associated with another entity.
- 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_69d85a1551a08190ba2caea7cd51c639 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e74ff70819094c1a85f51d6e228 |
completed | April 16, 2026, 1:42 a.m. |
| PD | Predicate disambiguation | batch_69ded27742a881909cd73cc5c7d062fd |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:19 a.m.