Triple
T37599985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lich King |
E935495
|
entity |
| Predicate | fusedFrom |
P164584
|
FINISHED |
| Object | Ner'zhul |
—
|
NE NERFINISHED |
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: Ner'zhul | Statement: [Lich King, fusedFrom, Ner'zhul]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fusedFrom Context triple: [Lich King, fusedFrom, Ner'zhul]
-
A.
unifiedFrom
chosen
Indicates that multiple separate entities or components have been combined into a single unified entity or representation.
-
B.
incorporatedFrom
Indicates that one entity was formed, established, or legally created by deriving or transforming from another pre-existing entity.
-
C.
integratedFrom
Indicates that something has been formed or constructed by combining or incorporating elements originating from another source.
-
D.
canonicalFusion
Indicates a standard or preferred way in which two or more entities are combined or merged into a single unified entity.
-
E.
frozenFrom
Indicates that one entity has been preserved or immobilized by being frozen starting from another entity, source, or prior state.
- 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.