Triple
T37599766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shadowmoon Valley (Draenor) |
E935490
|
entity |
| Predicate | magicTypePresence |
P21207
|
FINISHED |
| Object | fel magic |
—
|
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: fel magic | Statement: [Shadowmoon Valley (Draenor), magicTypePresence, fel magic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: magicTypePresence Context triple: [Shadowmoon Valley (Draenor), magicTypePresence, fel magic]
-
A.
meetsInPresenceOf
Indicates that two or more entities meet or interact while another specified entity is present as a witness, chaperone, or contextual participant.
-
B.
typeOfPresence
Indicates the manner or mode in which an entity is present or exists in relation to another entity, context, or environment.
-
C.
possiblePresenceIn
Indicates that an entity may be located in, occur in, or exist within a specified place, context, or container, without asserting that it is definitively present there.
-
D.
fieldPresence
chosen
Indicates that a particular field or attribute exists or is present within a given context, object, or dataset.
-
E.
mayPresent
Indicates that one entity is permitted or authorized to present, display, or introduce another entity or 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_69f76ecf39c081909baffe597bb55273 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:18 p.m.