Triple
T34481869
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Back to Basics |
E885207
|
entity |
| Predicate | hasDistinctiveStyleOf |
P68143
|
FINISHED |
| Object | Leo da Lion |
—
|
NE NERFINISHED |
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: Leo da Lion | Statement: [Back to Basics, hasDistinctiveStyleOf, Leo da Lion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDistinctiveStyleOf Context triple: [Back to Basics, hasDistinctiveStyleOf, Leo da Lion]
-
A.
personHasNotableStyle
Indicates that a person is recognized for having a distinctive or noteworthy style.
-
B.
inTheStyleOf
Indicates that one entity is created, performed, or presented in a manner that imitates or closely resembles the characteristic style of another entity.
-
C.
hasDistinctiveShape
Indicates that an entity possesses a shape or form that is notably different from others and can be easily recognized or distinguished.
-
D.
dedicatedToStyleOf
Indicates that something is devoted or specifically tailored to a particular style or manner of expression.
-
E.
fashionCharacteristic
chosen
Indicates a relationship where one entity possesses or exhibits a particular style, trend, or fashion-related attribute in relation to another.
- 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_69f349c947fc81909d30b53c194d6ea1 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff14d596e88190be5263b7f96a96cd |
completed | May 9, 2026, 11:04 a.m. |
| PD | Predicate disambiguation | batch_69ff13f0208081909369aeb3b77a6b1f |
completed | May 9, 2026, 11:01 a.m. |
Created at: May 1, 2026, 2:01 a.m.