Triple
T38583959
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Netherstorm |
E932303
|
entity |
| Predicate | loreFeature |
P187938
|
FINISHED |
| Object | site of Tempest Keep |
—
|
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: site of Tempest Keep | Statement: [Netherstorm, loreFeature, site of Tempest Keep]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: loreFeature Context triple: [Netherstorm, loreFeature, site of Tempest Keep]
-
A.
loreFunction
Indicates that something serves a narrative or world-building role within a fictional or informational context.
-
B.
loreType
Indicates the category or kind of lore that characterizes or classifies a given entity or subject.
-
C.
tourismFeature
Indicates that something serves as an attraction, amenity, or point of interest relevant to tourism or visitors.
-
D.
loreLocation
chosen
Indicates that something is the place or setting where related background story, history, or world-building information is situated or associated.
-
E.
lore
Indicates that information, stories, or knowledge about something is being told, recorded, or associated with it as part of a larger narrative or tradition.
- 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.