Triple
T34642053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michelle Pfeiffer as Claire Spencer |
E889585
|
entity |
| Predicate | studioBacklotFilming |
P44217
|
FINISHED |
| Object | Universal Studios (for house exteriors and sets) |
—
|
NE NERFINISHED |
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: Universal Studios (for house exteriors and sets) | Statement: [Michelle Pfeiffer as Claire Spencer, studioBacklotFilming, Universal Studios (for house exteriors and sets)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: studioBacklotFilming Context triple: [Michelle Pfeiffer as Claire Spencer, studioBacklotFilming, Universal Studios (for house exteriors and sets)]
-
A.
stateOfFilming
Indicates the location or jurisdiction (such as a state or region) where the filming of a work takes place.
-
B.
filmingStudio
Indicates that a studio is responsible for producing or filming a particular audiovisual work.
-
C.
placeOfShooting
Indicates the location where a shooting event took place.
-
D.
formerFilmingLocation
Indicates that a place was once used as a filming location for a work but is no longer used for that purpose.
-
E.
filmingLocationContext
chosen
Indicates the contextual relationship specifying where the filming of an event, scene, or production took place.
- 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_69f349d724848190b63ad3407e0006d9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f727bde8f88190ad746ca515134ca1 |
completed | May 3, 2026, 10:47 a.m. |
| PD | Predicate disambiguation | batch_69f72739c30c81908642eef3feb3afcf |
completed | May 3, 2026, 10:45 a.m. |
Created at: May 1, 2026, 2:04 a.m.