Triple
T11343888
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don Draper |
E268668
|
entity |
| Predicate | seriesFinaleScene |
P38927
|
FINISHED |
| Object | meditating at a California retreat |
—
|
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: meditating at a California retreat | Statement: [Don Draper, seriesFinaleScene, meditating at a California retreat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seriesFinaleScene Context triple: [Don Draper, seriesFinaleScene, meditating at a California retreat]
-
A.
seriesFinaleOf
Indicates that one work is the concluding or last installment of a particular series.
-
B.
laterFinale
Indicates that one event, episode, or occurrence serves as a concluding part that happens after another referenced event or finale.
-
C.
finalSceneAction
chosen
Indicates the action or event that occurs in the concluding or final scene of a narrative or sequence.
-
D.
seriesRunEnd
Indicates the point or event at which a series, sequence, or recurring run of something concludes.
-
E.
isFinalChapterOf
Indicates that one entity is the concluding or last chapter within the sequence of chapters of another entity (typically a work or volume).
- 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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d80148e2048190a716b515d78efdd1 |
completed | April 9, 2026, 7:43 p.m. |
| PD | Predicate disambiguation | batch_69d7e6f8aeb4819080476f16a69b2ee3 |
completed | April 9, 2026, 5:50 p.m. |
Created at: April 8, 2026, 9:33 p.m.