Triple
T19775027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Way of Light and Way of Darkness |
E474980
|
entity |
| Predicate | goalOfWayOfDarkness |
P108466
|
FINISHED |
| Object | death |
—
|
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: death | Statement: [Way of Light and Way of Darkness, goalOfWayOfDarkness, death]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: goalOfWayOfDarkness Context triple: [Way of Light and Way of Darkness, goalOfWayOfDarkness, death]
-
A.
turnsToDarkSide
Indicates that an entity undergoes a moral or ideological shift to join or embrace an evil, antagonistic, or “dark” faction or philosophy.
-
B.
typeOfDarkness
Indicates a relationship where one entity is characterized as a specific kind or form of darkness relative to another.
-
C.
goalOfRebelSide
Indicates that the specified goal is pursued or held by the rebel side in a conflict or opposition scenario.
-
D.
missionOfAntagonist
chosen
Indicates the primary goal, plan, or objective that the antagonist is actively pursuing.
-
E.
aimOfOtherSide
Indicates that one party’s goal or intended outcome is directed toward or defined in relation to the opposing or counterpart side in a relationship or interaction.
- 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_69d8e51a43a08190956bc6df13c91a77 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6535effcc819080a71de148759674 |
completed | April 20, 2026, 4:25 p.m. |
| PD | Predicate disambiguation | batch_69e53053ed2881908400becdfada7fd3 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:48 p.m.