Triple
T32668750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Washington at Princeton |
E835231
|
entity |
| Predicate | showsClothing |
P174781
|
FINISHED |
| Object | Continental Army uniform |
—
|
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: Continental Army uniform | Statement: [George Washington at Princeton, showsClothing, Continental Army uniform]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: showsClothing Context triple: [George Washington at Princeton, showsClothing, Continental Army uniform]
-
A.
garmentType
Indicates the specific kind or category of garment associated with an entity.
-
B.
fashionItem
Indicates that one entity is a fashion-related product or accessory associated with, used by, or worn by another entity.
-
C.
fashionCategory
Indicates the classification of an item into a specific fashion-related category or type (e.g., clothing, footwear, accessories).
-
D.
recommendedClothing
Indicates that one entity suggests or endorses a particular item of clothing as suitable or preferable for another entity or context.
-
E.
colorOfApparel
Indicates the specific color attribute associated with a piece of apparel or clothing item.
- 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_69f349303ccc8190a70d0f6e8a21d3fb |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6c7e32ec08190b74856937c4a9fc3 |
completed | May 3, 2026, 3:58 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f617c08190a70ba880210f908c |
completed | May 3, 2026, 3:41 a.m. |
| PDg | Predicate description generation | batch_69f6c77500a08190b2bdeca33bd2ac08 |
completed | May 3, 2026, 3:56 a.m. |
Created at: May 1, 2026, 1:08 a.m.