Triple
T32514125
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treehouse of Horror |
E831013
|
entity |
| Predicate | notInContinuityWith |
P161275
|
FINISHED |
| Object | main The Simpsons timeline |
—
|
NE NERFINISHED |
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: main The Simpsons timeline | Statement: [Treehouse of Horror, notInContinuityWith, main The Simpsons timeline]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notInContinuityWith Context triple: [Treehouse of Horror, notInContinuityWith, main The Simpsons timeline]
-
A.
isNotSequelTo
chosen
Indicates that one work does not follow another as a sequel in a narrative or release sequence.
-
B.
disruptsContinuityOf
Indicates that one entity interrupts, breaks, or otherwise prevents the ongoing, uninterrupted progression or sequence of another entity or process.
-
C.
cultContinuity
Indicates the continuation or persistence of a religious cult’s practices, beliefs, or traditions over time.
-
D.
notCoterminousWith
Indicates that two entities do not share the same boundaries in space, time, or extent and therefore are not exactly coincident.
-
E.
titleContinuity
Indicates that two works share a continuous or consistent use of the same title across versions, installments, or related contexts.
- 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_69f3492318348190ba37fb6b5f1d67f4 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c4a08a888190b7a25f185dae36f8 |
completed | May 3, 2026, 3:44 a.m. |
| PD | Predicate disambiguation | batch_69f6bd2a14b081908162923dfbf0a6f4 |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 1 a.m.