Triple
T34304378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sassafras |
E880267
|
entity |
| Predicate | rootsUsedFor |
P145108
|
FINISHED |
| Object | root beer flavoring (historically) |
—
|
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: root beer flavoring (historically) | Statement: [Sassafras, rootsUsedFor, root beer flavoring (historically)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rootsUsedFor Context triple: [Sassafras, rootsUsedFor, root beer flavoring (historically)]
-
A.
rootUse
Indicates that one entity serves as the primary or foundational use, function, or purpose of another entity.
-
B.
sideUsedBy
Indicates that a particular side or aspect of something is utilized or employed by a specified entity.
-
C.
areUsedBy
Indicates that certain entities serve as tools, resources, or means that are utilized or employed by other entities.
-
D.
usedByFor
chosen
Indicates that one entity makes use of another entity for a specific purpose or function.
-
E.
areUsedIn
Indicates that certain entities serve as components, tools, or resources within a particular process, context, or application.
- 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_69f349b79f6c81909cb468c92c39c74d |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f717836f0c8190b4a397bbac37dd09 |
completed | May 3, 2026, 9:38 a.m. |
| PD | Predicate disambiguation | batch_69f7127a2ff08190b77d00963c9df621 |
completed | May 3, 2026, 9:16 a.m. |
Created at: May 1, 2026, 1:57 a.m.