Triple
T3792182
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Julie Gillis |
E89677
|
entity |
| Predicate | primarySettingContext |
P48472
|
FINISHED |
| Object | nightclub scene |
—
|
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: nightclub scene | Statement: [Julie Gillis, primarySettingContext, nightclub scene]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primarySettingContext Context triple: [Julie Gillis, primarySettingContext, nightclub scene]
-
A.
primarySetting
Indicates that one entity serves as the main or central location, context, or environment in which the other entity’s events or activities primarily take place.
-
B.
primarySettingOf
Indicates that a location or context serves as the main or principal setting in which an entity (such as a story, event, or activity) takes place.
-
C.
primarySettingFeature
Indicates that a particular feature is the main or defining characteristic of a setting.
-
D.
primaryFunctionContext
Indicates the main situational or operational context in which a function, role, or process is primarily intended to be used or performed.
-
E.
primaryWorkContext
chosen
Indicates the main environment, setting, or domain in which an entity typically performs its work or primary activities.
- 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_69aed9597d6881909b6ee3b9de859223 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeecefa3608190a7a20ed6df6a64b2 |
completed | March 9, 2026, 3:53 p.m. |
| PD | Predicate disambiguation | batch_69aee743c8d08190a9f9c97b836bd703 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:15 p.m.