Triple
T38429497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hoovers |
E903758
|
entity |
| Predicate | fanTypeOriginal |
P13232
|
FINISHED |
| Object | centrifugal roof-mounted cooling fans |
—
|
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: centrifugal roof-mounted cooling fans | Statement: [Hoovers, fanTypeOriginal, centrifugal roof-mounted cooling fans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fanTypeOriginal Context triple: [Hoovers, fanTypeOriginal, centrifugal roof-mounted cooling fans]
-
A.
fanType
chosen
Indicates the specific category or kind of fan associated with an entity, such as its design, purpose, or operating principle.
-
B.
fanStyle
Indicates the manner or style in which a fan (supporter or admirer) expresses their fandom toward a subject.
-
C.
fanPosition
Indicates the spatial placement or orientation of a fan relative to a reference point or object.
-
D.
fangType
Indicates the specific kind or classification of fangs that an entity possesses.
-
E.
furnaceType
Indicates the specific kind or category of furnace associated with an entity.
- 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_69f76e6a2024819081aa04f4932f89d2 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcd1499e2c81909bafd84dc4810f45 |
completed | May 7, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69fcccf024ec819086383ffbb6cfc036 |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:31 p.m.