Triple
T9889482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | qipao |
E181416
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | hanfu |
E181415
|
NE 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: hanfu | Statement: [qipao, relatedTo, hanfu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: hanfu Context triple: [qipao, relatedTo, hanfu]
-
A.
Hanfu
chosen
Hanfu is the traditional historical clothing of the Han Chinese people, characterized by flowing robes, wide sleeves, and cross-collar designs that have influenced East Asian dress for centuries.
-
B.
qipao
The qipao, also known as the cheongsam, is a form-fitting traditional Chinese dress characterized by its high collar, side slits, and elegant silhouette.
-
C.
Hanbok
Hanbok is the traditional Korean attire characterized by vibrant colors, simple lines, and a graceful, flowing silhouette worn on special occasions and cultural ceremonies.
-
D.
Kimono
Kimono is a traditional Japanese full-length robe characterized by its T-shaped silhouette, wide sleeves, and sash belt called an obi.
-
E.
Kimono
Kimono was the original name of Kim Kardashian’s shapewear brand, later rebranded as SKIMS following public backlash over cultural appropriation concerns.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8283a6708190801af7a25a7ebb9f |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cdb47be2988190811a99dc56ae542a |
completed | April 2, 2026, 12:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1eb08075c81908e017df8048daba8 |
completed | April 5, 2026, 4:54 a.m. |
Created at: March 30, 2026, 8:39 p.m.