Triple
T36666549
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Savage |
E905279
|
entity |
| Predicate | fictionalUnitType |
P81118
|
FINISHED |
| Object | heavy bomber group |
—
|
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: heavy bomber group | Statement: [Frank Savage, fictionalUnitType, heavy bomber group]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fictionalUnitType Context triple: [Frank Savage, fictionalUnitType, heavy bomber group]
-
A.
featuresFictionalUnit
Indicates that something includes or presents a fictional unit (such as a character, group, or organization) as part of its content or structure.
-
B.
fictionalEntityType
chosen
Indicates that the subject is classified as a particular type or category of fictional entity within a narrative or imaginary context.
-
C.
unitTypes
Indicates that there is a relationship specifying the types or categories of units associated with an entity.
-
D.
portraysMilitaryUnit
Indicates that one entity visually or narratively represents, depicts, or shows a specific military unit.
-
E.
notableUnitType
Indicates that an entity is notably associated with, characterized by, or best known for a particular type of unit (such as an organizational, measurement, or structural unit).
- 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_69f76e6f10008190aea41746aa1b186e |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff397e19a88190a945b826159f5290 |
completed | May 9, 2026, 1:41 p.m. |
| PD | Predicate disambiguation | batch_69ff392400d0819088d30d08d4a774bd |
completed | May 9, 2026, 1:39 p.m. |
Created at: May 3, 2026, 4:12 p.m.