Triple
T3951878
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NATO bombing of Yugoslavia |
E84881
|
entity |
| Predicate | aircraftUsed |
P1524
|
FINISHED |
| Object | Tornado |
E148256
|
NE 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: Tornado | Statement: [NATO bombing of Yugoslavia, aircraftUsed, Tornado]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tornado Context triple: [NATO bombing of Yugoslavia, aircraftUsed, Tornado]
-
A.
Tornado
Tornado is a high-thrill water slide attraction featuring steep drops and a large funnel element, located at the Wet'n'Wild Gold Coast water park in Australia.
-
B.
Tornado F3
chosen
The Tornado F3 is a British twin-engine, two-seat air defense variant of the Panavia Tornado fighter aircraft, designed primarily for long-range interception missions.
-
C.
Tennessee Tornado
Tennessee Tornado is a steel looping roller coaster at Dollywood known for its intense drops, smooth inversions, and Appalachian mine-themed setting.
-
D.
Cyclone
Cyclone is a statically typed, safe dialect of C designed to prevent common programming errors such as buffer overflows and memory leaks while retaining low-level control.
-
E.
Cyclone
Cyclone is a family of low-cost, low-power FPGA devices developed by Altera (now part of Intel) for a wide range of embedded and programmable logic applications.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69aed934fbfc8190847068e4546de963 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef939d1308190930dc2c8272eafa4 |
completed | March 9, 2026, 4:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b533a80d4c8190bb1aac1b2900d9a8 |
completed | March 14, 2026, 10:08 a.m. |
Created at: March 9, 2026, 3:30 p.m.