Triple
T14507607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grand Jury Prize: Documentary at Sundance Film Festival |
E340305
|
entity |
| Predicate | typicalRuntimeOfEligibleWorks |
P74363
|
FINISHED |
| Object | feature-length |
—
|
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: feature-length | Statement: [Grand Jury Prize: Documentary at Sundance Film Festival, typicalRuntimeOfEligibleWorks, feature-length]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalRuntimeOfEligibleWorks Context triple: [Grand Jury Prize: Documentary at Sundance Film Festival, typicalRuntimeOfEligibleWorks, feature-length]
-
A.
typicalRuntimeRange
Indicates the usual lower and upper bounds of time typically required for an entity to run or complete its operation.
-
B.
typicalRuntimePerShort
Indicates the usual or average amount of time it takes to complete a short instance of the referenced activity or process.
-
C.
hasTypicalPerformanceDuration
Indicates the usual or expected length of time that a performance or activity typically lasts.
-
D.
hasRunningTimeCategory
chosen
Indicates that an entity is associated with a specific category based on its running time or duration.
-
E.
typicalCompletionTimeInWeeks
Indicates the usual number of weeks it takes to complete the associated task, process, or activity.
- 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_69d822d9c0408190b9a2b3643e58bb4d |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69de94e40e44819084f323f8f9982b75 |
completed | April 14, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69de5c4ccba08190a988bfda0bc9f5cb |
completed | April 14, 2026, 3:25 p.m. |
Created at: April 10, 2026, 1:21 a.m.