Triple
T12113198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Devotion bag |
E288485
|
entity |
| Predicate | hasDetailing |
P102862
|
FINISHED |
| Object | decorative stitching |
—
|
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: decorative stitching | Statement: [Devotion bag, hasDetailing, decorative stitching]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDetailing Context triple: [Devotion bag, hasDetailing, decorative stitching]
-
A.
hasBodyShop
Indicates that one entity operates, owns, or is associated with an auto body repair shop.
-
B.
hasGrooming
Indicates that one entity performs grooming behavior on, or receives grooming from, another entity.
-
C.
serviceDetail
chosen
Indicates the specific characteristics, parameters, or components that further describe or qualify a service.
-
D.
hasWorkDetail
Indicates that an entity is associated with specific information or attributes about its work or job-related details.
-
E.
sawExtensiveService
Indicates that the subject was used or employed heavily and over a long period of time, often in an operational or practical capacity.
- 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_69d6ab4a5c448190a110d1273314b21a |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9164ada5081908676bd9e5947268a |
completed | April 10, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69d9150497408190921334d21503375a |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:49 p.m.