Triple
T14242471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lisa the Simpson |
E353044
|
entity |
| Predicate | openingSequenceGag |
P52455
|
FINISHED |
| Object | couch gag |
—
|
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: couch gag | Statement: [Lisa the Simpson, openingSequenceGag, couch gag]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openingSequenceGag Context triple: [Lisa the Simpson, openingSequenceGag, couch gag]
-
A.
openingCatchphrase
Indicates that one entity is a characteristic phrase or line regularly used by another entity at the beginning of a recurring performance, appearance, or communication.
-
B.
openingNarrativeDevice
Indicates the narrative device or technique used to begin or introduce a story or discourse.
-
C.
openingSequenceFormat
Indicates the specific structural or stylistic format used for an opening sequence in a work or presentation.
-
D.
openingNarrationBy
Indicates that an entity serves as the narrator delivering the opening narration for another entity (such as a work or production).
-
E.
notableGag
chosen
Indicates that something features a particularly memorable or significant joke, comedic moment, or running gag.
- 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_69d8278adc7c8190a9218d69bce3c4e6 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6244ad188190b9d9db7914240410 |
completed | April 14, 2026, 3:50 p.m. |
| PD | Predicate disambiguation | batch_69de05bf069c8190b69f00f00f5eb126 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 10, 2026, 1:08 a.m.