Triple
T35081410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Within the Woods |
E1012446
|
entity |
| Predicate | initialExhibitionVenue |
P8425
|
FINISHED |
| Object | midnight movie screenings |
—
|
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: midnight movie screenings | Statement: [Within the Woods, initialExhibitionVenue, midnight movie screenings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialExhibitionVenue Context triple: [Within the Woods, initialExhibitionVenue, midnight movie screenings]
-
A.
exhibitedBeforeInstallationAt
Indicates that an item was publicly displayed or shown prior to being installed at a particular location or in a specific context.
-
B.
previousExhibitionLocation
Indicates that a given location was the site where an exhibition was held immediately before its current or another specified exhibition location.
-
C.
displayPositionAtFirstExhibition
Indicates that an entity was assigned a specific display position during its first exhibition.
-
D.
firstExhibited
chosen
Indicates the event or context in which something was publicly displayed or presented for the first time.
-
E.
exhibitLocation
Indicates the place or venue where something is displayed, presented, or put on exhibit.
- 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_69f76dd32c008190853aef6028f60208 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fcec5f8b448190b48330a19b462d24 |
completed | May 7, 2026, 7:47 p.m. |
| PD | Predicate disambiguation | batch_69fceaf1e23881908ca24160a638e329 |
completed | May 7, 2026, 7:41 p.m. |
Created at: May 3, 2026, 4:01 p.m.