Triple
T4905563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Overholt distillery |
E109905
|
entity |
| Predicate | brandAgeCharacteristic |
P15065
|
FINISHED |
| Object | one of the longest-lived American whiskey brands |
—
|
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: one of the longest-lived American whiskey brands | Statement: [Old Overholt distillery, brandAgeCharacteristic, one of the longest-lived American whiskey brands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: brandAgeCharacteristic Context triple: [Old Overholt distillery, brandAgeCharacteristic, one of the longest-lived American whiskey brands]
-
A.
containsAge
Indicates that one entity includes or specifies the age value or age-related information of another entity.
-
B.
brandFounded
Indicates that a specific brand was established or created at a particular point in time or by a particular founder or entity.
-
C.
brandAttribute
chosen
Indicates that a specific attribute or characteristic is associated with, or describes, a particular brand.
-
D.
serviceAge
Indicates the length of time an entity has been in service or actively performing its role.
-
E.
vineAge
Indicates the age or length of time that a vine has been growing or established.
- 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_69bd441180708190ba42ffb44fea533a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6e71a5c481909f5862bf497c3c9d |
completed | March 20, 2026, 3:57 p.m. |
| PD | Predicate disambiguation | batch_69bd6c325e188190823836d79934e9bc |
completed | March 20, 2026, 3:48 p.m. |
Created at: March 20, 2026, 1:29 p.m.