Triple
T6849453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sandy Saddler |
E157977
|
entity |
| Predicate | styleCharacterization |
P48733
|
FINISHED |
| Object | aggressive, powerful puncher |
—
|
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: aggressive, powerful puncher | Statement: [Sandy Saddler, styleCharacterization, aggressive, powerful puncher]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: styleCharacterization Context triple: [Sandy Saddler, styleCharacterization, aggressive, powerful puncher]
-
A.
characterStyle
Indicates how a character is visually or typographically presented, such as its font, weight, size, or decorative attributes.
-
B.
scopeCharacterization
Indicates how the extent, boundaries, or coverage of something is defined, described, or qualified in relation to another entity or context.
-
C.
ruleCharacterization
Indicates that one rule is described, defined, or characterized in terms of another rule or set of rules.
-
D.
styleDescribedAs
chosen
Indicates that the manner, aesthetic, or mode of something is characterized or labeled using a particular style description.
-
E.
languageCharacterizedBy
Indicates that a language is defined or distinguished by a particular feature, property, or characteristic.
- 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_69c6882fae988190864cbba788c5ebb4 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d84acb288190a67d974197ecab2f |
completed | March 27, 2026, 7:19 p.m. |
| PD | Predicate disambiguation | batch_69c6d0a12834819097d7e6c0b823745e |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:20 p.m.