Triple
T9873421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Midnight (Sundance section) |
E240014
|
entity |
| Predicate | screeningTime |
P90991
|
FINISHED |
| Object | late night |
—
|
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: late night | Statement: [Midnight (Sundance section), screeningTime, late night]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: screeningTime Context triple: [Midnight (Sundance section), screeningTime, late night]
-
A.
typicalScreeningTime
Indicates the usual or standard amount of time allocated for a screening to take place.
-
B.
screeningType
Indicates the specific method or category of screening applied in a screening process or evaluation.
-
C.
hasScreenTimeIn
Indicates that an entity appears on screen for a certain duration within a specified audiovisual work or segment.
-
D.
screeningBasis
Indicates the underlying reason, criterion, or grounds on which a screening or evaluation is conducted between entities.
-
E.
hasRunningTimeCategory
Indicates that an entity is associated with a specific category based on its running time or duration.
- F. None of above. chosen
Provenance (4 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_69ca84e8a0788190b9061811d50fd554 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb3f754008190abe3fe034b42908e |
completed | April 2, 2026, 12:10 a.m. |
| PD | Predicate disambiguation | batch_69cd1d7621d48190aa6a6f34399514b0 |
completed | April 1, 2026, 1:28 p.m. |
| PDg | Predicate description generation | batch_69cd3581a9688190a00cef4c3eebb0ae |
completed | April 1, 2026, 3:10 p.m. |
Created at: March 30, 2026, 8:37 p.m.