Triple
T34208157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Italian wolf |
E877572
|
entity |
| Predicate | averagePackSize |
P133102
|
FINISHED |
| Object | 2–7 individuals |
—
|
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: 2–7 individuals | Statement: [Italian wolf, averagePackSize, 2–7 individuals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: averagePackSize Context triple: [Italian wolf, averagePackSize, 2–7 individuals]
-
A.
typicalPackSize
chosen
Indicates the usual quantity of items contained together in a single package for that entity.
-
B.
packagingSize
Indicates the specific quantity or physical dimensions in which a product is packaged for sale or distribution.
-
C.
maximumPackSize
Indicates the largest number of items or units that are allowed or intended to be grouped together in a single pack.
-
D.
typicalUnitSize
Indicates the standard or most common size or quantity in which something is typically measured, packaged, or used.
-
E.
librarySizeApprox
Indicates that the size of a library (e.g., number of items, capacity, or volume) is known or treated as an approximate value 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_69f349aff5f0819096275315abea5344 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71052707c8190b6b514bf87a4bc79 |
completed | May 3, 2026, 9:07 a.m. |
| PD | Predicate disambiguation | batch_69f70f3c5bfc81908585f52e196dafe5 |
completed | May 3, 2026, 9:02 a.m. |
Created at: May 1, 2026, 1:55 a.m.