Triple
T27051253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chou |
E684777
|
entity |
| Predicate | hasMakeupFeature |
P78811
|
FINISHED |
| Object | small white patch on the nose |
—
|
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: small white patch on the nose | Statement: [Chou, hasMakeupFeature, small white patch on the nose]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMakeupFeature Context triple: [Chou, hasMakeupFeature, small white patch on the nose]
-
A.
hasMakeupEffectsBy
Indicates that the makeup effects for an entity (such as a film or production) are created or supervised by a specified person or team.
-
B.
facialMakeupIndicates
Indicates that the presence, style, or characteristics of facial makeup convey or signify a particular state, role, identity, or condition of an entity.
-
C.
makeupType
chosen
Indicates the specific kind or category of makeup associated with an entity.
-
D.
usesMakeupStyle
Indicates that one entity applies or adopts the makeup style or technique associated with another entity.
-
E.
usesStageMakeup
Indicates that one entity applies or wears theatrical or stage makeup in relation to another entity or context.
- 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_69ef14829fac8190914bef9ecc3005d7 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69fda94697c4819081291967202248be |
completed | May 8, 2026, 9:13 a.m. |
| PD | Predicate disambiguation | batch_69fda5973fcc8190a57daef31fb70a49 |
completed | May 8, 2026, 8:57 a.m. |
Created at: April 27, 2026, 8:14 a.m.