Triple
T36349450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Remember Sammy Jankis |
E895154
|
entity |
| Predicate | linkedToPlotPoint |
P146205
|
FINISHED |
| Object | backstory of Sammy Jankis |
—
|
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: backstory of Sammy Jankis | Statement: [Remember Sammy Jankis, linkedToPlotPoint, backstory of Sammy Jankis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linkedToPlotPoint Context triple: [Remember Sammy Jankis, linkedToPlotPoint, backstory of Sammy Jankis]
-
A.
connectedToPlotElement
chosen
Indicates that one element is linked or related to a specific plot element within a narrative structure.
-
B.
linkedPosition
Indicates that one position is associated or connected to another position in a defined way.
-
C.
linkedLocation
Indicates that one location is associated or connected to another location in a meaningful way, such as being related, referenced, or contextually tied.
-
D.
isKeyToPlotOf
Indicates that something plays a crucial, defining role in driving or enabling the main events or structure of a plot.
-
E.
plotElement
Indicates that one entity functions as a narrative component or structural element within the storyline of another entity (such as a work of fiction or media).
- 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_69f76e4f437c8190a1af3ea2564f41f5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69feb5e66224819083b87c3707a5a5e0 |
completed | May 9, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69feb3bd700c8190991ed200cd3c04db |
completed | May 9, 2026, 4:10 a.m. |
Created at: May 3, 2026, 4:09 p.m.