Triple
T38645529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanctum of the Mad |
E938703
|
entity |
| Predicate | hasLoreElement |
P99630
|
FINISHED |
| Object | madness |
—
|
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: madness | Statement: [Sanctum of the Mad, hasLoreElement, madness]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLoreElement Context triple: [Sanctum of the Mad, hasLoreElement, madness]
-
A.
hasLoreItemType
Indicates that an entity is associated with, or categorized by, a specific type of lore-related item.
-
B.
hasLoreContext
chosen
Indicates that something is associated with or situated within a particular narrative, historical, or fictional background or storyline.
-
C.
hasLoreRole
Indicates that an entity holds a specific narrative, mythological, or story-related role in relation to another entity or context.
-
D.
materialInLore
Indicates that a material is referenced, described, or plays a role within a body of lore or fictional/worldbuilding context.
-
E.
hasMagicItem
Indicates that an entity possesses or is associated with a magical item.
- 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_69f76ed948ec81908ce7811608a8f359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ffe6e2eb688190a45fd2c6415cd86a |
completed | May 10, 2026, 2:01 a.m. |
| PD | Predicate disambiguation | batch_69ffe65939488190a35b9c2e9c7ad868 |
completed | May 10, 2026, 1:58 a.m. |
Created at: May 3, 2026, 4:32 p.m.