Triple
T36524793
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Statesman whiskey |
E900271
|
entity |
| Predicate | hasFictionalProductCategory |
P117060
|
FINISHED |
| Object | American whiskey |
—
|
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: American whiskey | Statement: [Statesman whiskey, hasFictionalProductCategory, American whiskey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFictionalProductCategory Context triple: [Statesman whiskey, hasFictionalProductCategory, American whiskey]
-
A.
hasFictionalProduct
Indicates a relationship where one entity features, offers, or includes a product that exists only in fiction or an imagined context.
-
B.
hasFictionalType
chosen
Indicates that an entity is associated with or classified under a particular type or category that is fictional rather than real.
-
C.
hasFictionalPackaging
Indicates that an item is presented or wrapped in packaging that is imaginary, simulated, or not used in real-world distribution.
-
D.
hasFictionalContent
Indicates that something contains or includes material that is imaginary, invented, or not intended to represent real events or facts.
-
E.
hasFictionalMarketing
Indicates that an entity is associated with marketing materials or campaigns that are fictional, fabricated, or not based on real products, services, or events.
- 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_69f76e5eedb88190a393b8c623f71dd7 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a002103c93081908398fa5726f5fa6e |
completed | May 10, 2026, 6:09 a.m. |
| PD | Predicate disambiguation | batch_6a001fcb9fb48190a27d8f2ca983fbe6 |
completed | May 10, 2026, 6:03 a.m. |
Created at: May 3, 2026, 4:11 p.m.