Triple
T5199989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emilio Largo |
E117368
|
entity |
| Predicate | plotInThunderball |
P17462
|
FINISHED |
| Object | hijacking NATO bomber with nuclear bombs |
—
|
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: hijacking NATO bomber with nuclear bombs | Statement: [Emilio Largo, plotInThunderball, hijacking NATO bomber with nuclear bombs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: plotInThunderball Context triple: [Emilio Largo, plotInThunderball, hijacking NATO bomber with nuclear bombs]
-
A.
plotInvolvement
chosen
Indicates that an entity participates in, contributes to, or is affected by the events or storyline of a narrative work.
-
B.
bombPlacement
Indicates the act of positioning or installing a bomb at a specific location or target.
-
C.
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).
-
D.
game5Location
Indicates the location where the fifth game in a series or sequence takes place.
-
E.
centralPlotDevice
Indicates that one entity functions as the main narrative mechanism or element around which the plot of the other entity is structured.
- 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_69bd4462ed04819084fcb01eb9d2fa74 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7adb034c819086bf8a85fbf158f4 |
completed | March 20, 2026, 4:50 p.m. |
| PD | Predicate disambiguation | batch_69bd77b9a67c8190819612257ea746b4 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:47 p.m.