Triple
T28762
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alcohol and Tobacco Tax and Trade Bureau |
E572
|
entity |
| Predicate | collects |
P2196
|
FINISHED |
| Object | federal excise taxes on distilled spirits |
—
|
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: federal excise taxes on distilled spirits | Statement: [Alcohol and Tobacco Tax and Trade Bureau, collects, federal excise taxes on distilled spirits]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collects Context triple: [Alcohol and Tobacco Tax and Trade Bureau, collects, federal excise taxes on distilled spirits]
-
A.
collectionStrength
Indicates the degree or intensity of association or cohesion among items within a collection.
-
B.
complements
Indicates that one entity enhances, completes, or improves another by providing qualities or functions that fit well together.
-
C.
collectionSize
Indicates the total number of items contained within a specified collection.
-
D.
attracts
Indicates that one entity exerts a force or influence that draws another entity toward it.
-
E.
includes
Indicates that one entity contains, encompasses, or has another entity as a part, member, or subset.
- F. None of above. chosen
Provenance (4 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_69a2479dec388190967ba648663442c9 |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a24925607c8190a9ce7ec834f3e5bb |
completed | Feb. 28, 2026, 1:47 a.m. |
| PD | Predicate disambiguation | batch_69a2486bd74c81908d32be3c7d22f51f |
completed | Feb. 28, 2026, 1:44 a.m. |
| PDg | Predicate description generation | batch_69a249246968819099985f13127063d2 |
completed | Feb. 28, 2026, 1:47 a.m. |
Created at: Feb. 28, 2026, 1:44 a.m.