Triple
T10445265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hercule Poirot film series (Kenneth Branagh) |
E246269
|
entity |
| Predicate | featuresSettingStyle |
P32516
|
FINISHED |
| Object | lavish period settings |
—
|
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: lavish period settings | Statement: [Hercule Poirot film series (Kenneth Branagh), featuresSettingStyle, lavish period settings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresSettingStyle Context triple: [Hercule Poirot film series (Kenneth Branagh), featuresSettingStyle, lavish period settings]
-
A.
featuresStyle
Indicates that one entity exhibits, incorporates, or is characterized by a particular style associated with another entity.
-
B.
featuresSetting
chosen
Indicates that something includes, presents, or highlights a particular setting as a notable or primary aspect.
-
C.
stylingFeature
Indicates a visual or design-related characteristic applied to an entity, such as formatting, layout, or aesthetic treatment.
-
D.
stylingTool
Indicates a tool or instrument used to style, shape, or arrange something (typically hair, clothing, or design elements).
-
E.
stylingEnables
Indicates that one entity provides or activates styling capabilities or visual formatting for 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_69d381c04fe08190957c26c526a3b05a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4fe083cd881909d2d8ad75d1d94cb |
completed | April 7, 2026, 12:52 p.m. |
| PD | Predicate disambiguation | batch_69d4fb73a5e48190a8df4775bc5da80f |
completed | April 7, 2026, 12:41 p.m. |
Created at: April 6, 2026, 12:16 p.m.