Triple
T35207201
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ayleids |
E1016567
|
entity |
| Predicate | magicFocus |
P183776
|
FINISHED |
| Object | light and starlight manipulation |
—
|
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: light and starlight manipulation | Statement: [Ayleids, magicFocus, light and starlight manipulation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: magicFocus Context triple: [Ayleids, magicFocus, light and starlight manipulation]
-
A.
focusMode
Indicates that an entity is currently in a concentrated or distraction-minimized state directed toward a specific task, target, or context.
-
B.
focusShift
Indicates a change in attention or emphasis from one entity or topic to another.
-
C.
instrumentFocus
Indicates that the relationship or action specifically emphasizes or centers on the instrument used to perform it.
-
D.
focusFeature
Indicates that one entity is the primary or emphasized feature, aspect, or attribute being highlighted or concentrated on in relation to another.
-
E.
focusModeSwitch
Indicates switching the state of an entity into or out of a designated focus mode.
- 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_69f76ddf549c8190869d0af076fd2c28 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7a283388c81908e4a9ee3369e8d6f |
completed | May 3, 2026, 7:31 p.m. |
| PD | Predicate disambiguation | batch_69f7a06d4f108190bae3ab9ae431d2c7 |
completed | May 3, 2026, 7:22 p.m. |
| PDg | Predicate description generation | batch_69f7a224365081908ff6958e3b30bd05 |
completed | May 3, 2026, 7:29 p.m. |
Created at: May 3, 2026, 4:02 p.m.