Triple
T8790140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Merle Oberon |
E209140
|
entity |
| Predicate | usedMakeupToConceal |
P65448
|
FINISHED |
| Object | facial scars |
—
|
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: facial scars | Statement: [Merle Oberon, usedMakeupToConceal, facial scars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedMakeupToConceal Context triple: [Merle Oberon, usedMakeupToConceal, facial scars]
-
A.
makeupType
Indicates the specific kind or category of makeup associated with an entity.
-
B.
usesStageMakeup
Indicates that one entity applies or wears theatrical or stage makeup in relation to another entity or context.
-
C.
cosmeticCategory
Indicates that one entity is classified as belonging to a particular cosmetic or beauty product category defined by the other entity.
-
D.
usesMasksOrDisguises
Indicates that an entity employs masks, costumes, or other forms of disguise to conceal or alter its identity in the context of an action or interaction.
-
E.
usedCover
chosen
Indicates that one entity employed another entity as a protective or concealing cover in a given 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_69ca836168108190bb43d3dc235c1f55 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5f8d25f881908863d636fa57a8a2 |
completed | March 31, 2026, 11:58 p.m. |
| PD | Predicate disambiguation | batch_69cc5c1d48f08190b325a77d4c76d223 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:43 p.m.