Triple
T10272481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peking duck |
E240871
|
entity |
| Predicate | skinPreparation |
P47540
|
FINISHED |
| Object | air pumped between skin and meat |
—
|
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: air pumped between skin and meat | Statement: [Peking duck, skinPreparation, air pumped between skin and meat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: skinPreparation Context triple: [Peking duck, skinPreparation, air pumped between skin and meat]
-
A.
bodyTreatment
Indicates a treatment or therapeutic procedure that is applied to a person's body.
-
B.
preparesFor
Indicates that one entity is used, designed, or undertaken in order to get another entity ready for a future event, state, or activity.
-
C.
preparationInvolved
chosen
Indicates that a particular preparation, process, or setup is involved in enabling or carrying out an action, event, or relationship.
-
D.
skinCharacteristic
Indicates a relationship where an entity is associated with a particular quality, feature, or condition of its skin.
-
E.
preparationBy
Indicates that one entity is created, assembled, or made ready through the actions or processes performed by another entity.
- 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_69d381a94c1881908fc38fc263d9b9c2 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d2872830819080fdfa816167d04c |
completed | April 7, 2026, 9:46 a.m. |
| PD | Predicate disambiguation | batch_69d4d1ef6e6c81908a8ee52e4d28127b |
completed | April 7, 2026, 9:44 a.m. |
Created at: April 6, 2026, 11:36 a.m.