Triple
T35471854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vanguard Commander for Hunters |
E1025226
|
entity |
| Predicate | loreCategory |
P99966
|
FINISHED |
| Object | Vanguard |
—
|
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: Vanguard | Statement: [Vanguard Commander for Hunters, loreCategory, Vanguard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: loreCategory Context triple: [Vanguard Commander for Hunters, loreCategory, Vanguard]
-
A.
loreType
chosen
Indicates the category or kind of lore that characterizes or classifies a given entity or subject.
-
B.
agingCategory
Indicates the classification of an entity based on its stage or degree of aging.
-
C.
culturalCategory
Indicates that one entity classifies or groups another entity according to a particular culture, tradition, or culturally defined type.
-
D.
culturalHeritageCategory
Indicates the classification of something according to its type or category within cultural heritage (e.g., monument, tradition, artifact).
-
E.
areaTheme
Indicates that a particular theme, topic, or subject is associated with or characterizes a given area or region.
- 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_69f76dfadba0819083456aadcd6864ea |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79da9f80c8190b0afd8509f28747b |
completed | May 3, 2026, 7:10 p.m. |
| PD | Predicate disambiguation | batch_69f79617d40481909ba372f94209c08b |
completed | May 3, 2026, 6:38 p.m. |
Created at: May 3, 2026, 4:04 p.m.