Triple
T3150356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goodnights |
E65861
|
entity |
| Predicate | recursEvery |
P7174
|
FINISHED |
| Object | episode of Saturday Night Live |
—
|
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: episode of Saturday Night Live | Statement: [Goodnights, recursEvery, episode of Saturday Night Live]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recursEvery Context triple: [Goodnights, recursEvery, episode of Saturday Night Live]
-
A.
recurs
Indicates that an event, condition, or pattern happens again, often repeatedly or at regular intervals, after having occurred before.
-
B.
occursEvery
chosen
Indicates that an event or action happens repeatedly at regular, specified intervals.
-
C.
recurrence
Indicates that an event, condition, or state happens again or repeatedly over time, often after a period of absence or resolution.
-
D.
recurringEvent
Indicates that an event occurs repeatedly over time according to some regular pattern or schedule.
-
E.
recurringLocation
Indicates that an event, action, or state happens repeatedly at the specified location over time.
- 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_69ad8584485081909ed529e890cadc4a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada5bf902c8190a490fa55e2dcecc0 |
completed | March 8, 2026, 4:37 p.m. |
| PD | Predicate disambiguation | batch_69ad9dfa3d9081908425aa636bb9b897 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:05 p.m.