Triple
T23168618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | fish and brewis |
E578780
|
entity |
| Predicate | traditionalFatSource |
P119205
|
FINISHED |
| Object | pork fat |
—
|
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: pork fat | Statement: [fish and brewis, traditionalFatSource, pork fat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalFatSource Context triple: [fish and brewis, traditionalFatSource, pork fat]
-
A.
traditionalFat
chosen
Indicates that an entity uses or contains a type or amount of fat characteristic of customary or long-established practices.
-
B.
typicalFatContent
Indicates the usual or characteristic amount of fat contained in something, such as a food or product.
-
C.
fattyAcid
Indicates a relationship where one entity is a fatty acid component, derivative, or participant in a process involving another entity.
-
D.
traditionalFilling
Indicates that something is filled using a customary or historically established type of filling associated with a particular practice, item, or cuisine.
-
E.
fatColor
Indicates the color characteristic associated with an entity’s fat or fatty tissue.
- 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_69e245fc75348190a0288401044c8af8 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f2e5e208190839ec37de4b974af |
completed | April 29, 2026, 4:55 a.m. |
| PD | Predicate disambiguation | batch_69ef89ff76808190808ee4ad9dea776b |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:03 p.m.