Triple
T16710020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. Petersburg graveyard |
E406081
|
entity |
| Predicate | timeOfKeyScene |
P124316
|
FINISHED |
| Object | midnight |
—
|
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 | Statement: [St. Petersburg graveyard, timeOfKeyScene, midnight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfKeyScene Context triple: [St. Petersburg graveyard, timeOfKeyScene, midnight]
-
A.
openingSceneTime
Indicates the specific time at which the opening scene of a work (e.g., film, play, or episode) takes place within its narrative.
-
B.
timeToControl
Indicates the amount of time required for an entity to gain or establish control over another entity, process, or situation.
-
C.
timeCoMainEvent
Indicates that two or more events occur as co-main events at the same time or within the same overarching event timeframe.
-
D.
timeScatteredAcross
Indicates that instances or occurrences of something are distributed over multiple, non-contiguous points in time rather than concentrated in a single continuous period.
-
E.
finalSceneAction
Indicates the action or event that occurs in the concluding or final scene of a narrative or sequence.
- 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_69d8838db21081909589220fd71440a4 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3865186b48190bb45a761f5cf1a83 |
completed | April 18, 2026, 1:25 p.m. |
| PD | Predicate disambiguation | batch_69e319c379f88190ac0adf812486f598 |
completed | April 18, 2026, 5:42 a.m. |
| PDg | Predicate description generation | batch_69e326b9e84881909a9166e65bd850d6 |
completed | April 18, 2026, 6:37 a.m. |
Created at: April 10, 2026, 5:20 a.m.