Triple
T4063229
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I taste a liquor never brewed |
E86263
|
entity |
| Predicate | imagerySourceDomain |
P17123
|
FINISHED |
| Object | alcohol |
—
|
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: alcohol | Statement: [I taste a liquor never brewed, imagerySourceDomain, alcohol]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: imagerySourceDomain Context triple: [I taste a liquor never brewed, imagerySourceDomain, alcohol]
-
A.
usesImageryOf
chosen
Indicates that one entity employs or incorporates visual or sensory imagery that depicts, references, or symbolically represents another entity.
-
B.
mapsFrom
Indicates that one entity is derived, transformed, or constructed based on data, structure, or content originating from another entity.
-
C.
cartographicAuthority
Indicates that an entity has official responsibility for creating, maintaining, or validating cartographic or map-related information for another entity or area.
-
D.
inputDomain
Indicates that a function, process, or system accepts inputs belonging to a specified domain or set of allowable values.
-
E.
imagedBy
Indicates that something is captured, recorded, or represented in an image created by a particular imaging device, method, or agent.
- 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_69aed93c69208190a4efac0efe3cd69b |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefd0bdea48190805a79515ee92709 |
completed | March 9, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69aef90438908190a005b08ba271eacf |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:38 p.m.