Triple
T33704254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Filet mignon |
E863540
|
entity |
| Predicate | commonThickness |
P156439
|
FINISHED |
| Object | about 1 to 2 inches |
—
|
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: about 1 to 2 inches | Statement: [Filet mignon, commonThickness, about 1 to 2 inches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commonThickness Context triple: [Filet mignon, commonThickness, about 1 to 2 inches]
-
A.
thickerThan
Indicates that one entity has a greater thickness (is more thick) than another entity.
-
B.
hasThicknessRange
chosen
Indicates that an entity is associated with a minimum and maximum thickness value defining the range of its thickness.
-
C.
thickness
Indicates the measure of how deep or wide an object or layer is from one surface or side to its opposite.
-
D.
wallThicknessComparedTo
Indicates how the thickness of one wall relates to the thickness of another wall, typically in terms of being greater, equal, or less.
-
E.
hasApproximateAverageThickness
Indicates that an entity possesses a thickness value that is an estimated or typical average rather than an exact measurement.
- 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_69f3498844608190bb8f9b14908d2510 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fe920a437081908d5174e8cf7a53a6 |
completed | May 9, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69fe919a9a6c8190acb4483f386e6db7 |
completed | May 9, 2026, 1:44 a.m. |
Created at: May 1, 2026, 1:43 a.m.