Triple
T23330903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lisa Loeb |
E591436
|
entity |
| Predicate | eyeWearStyle |
P66471
|
FINISHED |
| Object | cat-eye glasses |
—
|
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: cat-eye glasses | Statement: [Lisa Loeb, eyeWearStyle, cat-eye glasses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eyeWearStyle Context triple: [Lisa Loeb, eyeWearStyle, cat-eye glasses]
-
A.
hasEyeWear
chosen
Indicates that one entity is wearing or equipped with some form of eyewear (such as glasses, goggles, or similar eye accessories).
-
B.
earType
Indicates the specific kind or classification of ears associated with an entity.
-
C.
glassesFunction
Indicates that one entity serves as the functional purpose or use associated with a pair of glasses for another entity.
-
D.
eyeType
Indicates the specific kind or category of eyes an entity has, such as their form, structure, or visual style.
-
E.
wearIndicates
Indicates that one entity is wearing or has clothing or an accessory on its body, typically as a visible or functional item.
- 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_69e25d20156c81908c5c53195bd9c738 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f197ece360819099da8443dd86a355 |
completed | April 29, 2026, 5:32 a.m. |
| PD | Predicate disambiguation | batch_69effcf8ca2c8190887d4f4656617d21 |
completed | April 28, 2026, 12:19 a.m. |
Created at: April 17, 2026, 5:15 p.m.