Triple
T7467798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rigu |
E176418
|
entity |
| Predicate | wrappingStyle |
P76427
|
FINISHED |
| Object | wrapped around the waist |
—
|
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: wrapped around the waist | Statement: [Rigu, wrappingStyle, wrapped around the waist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wrappingStyle Context triple: [Rigu, wrappingStyle, wrapped around the waist]
-
A.
supportsWordWrap
Indicates that one entity provides or enables automatic wrapping of text onto the next line instead of extending it horizontally.
-
B.
passingStyle
Indicates the manner or technique by which something (typically a ball or object) is passed from one entity to another.
-
C.
compositionStyle
Indicates the characteristic manner or approach in which something is composed, such as its structural, aesthetic, or stylistic conventions.
-
D.
marginStyle
Indicates how the margins around an element are styled or configured in relation to surrounding content.
-
E.
endingStyle
Indicates the manner or stylistic form in which something concludes or is brought to an end.
- 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_69c69f223fd88190b4c69b95d7cbeeda |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f3f589cc81909f25268838c7c964 |
completed | March 27, 2026, 9:17 p.m. |
| PD | Predicate disambiguation | batch_69c6f03d967081908a8e696ff9693b90 |
completed | March 27, 2026, 9:01 p.m. |
| PDg | Predicate description generation | batch_69c6f105e320819091db3cdb1f1351f0 |
completed | March 27, 2026, 9:05 p.m. |
Created at: March 27, 2026, 3:40 p.m.