Triple
T28337643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caproni Ca.60 Noviplano |
E717720
|
entity |
| Predicate | pilotInCrash |
P89185
|
FINISHED |
| Object | Federico Semprini |
—
|
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: Federico Semprini | Statement: [Caproni Ca.60 Noviplano, pilotInCrash, Federico Semprini]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pilotInCrash Context triple: [Caproni Ca.60 Noviplano, pilotInCrash, Federico Semprini]
-
A.
pilotAtFatalCrash
chosen
Indicates that the specified person was serving as the pilot at the time and location of a fatal crash.
-
B.
crashLandsIn
Indicates that an entity descends and lands in a location or object in an uncontrolled or damaging manner.
-
C.
aircraftImpact
Indicates that an aircraft collides with or crashes into a target or surface, causing an impact event.
-
D.
aircraftAccident
Indicates that an event involves an aircraft experiencing an accident, such as a crash, collision, or serious malfunction during operation.
-
E.
missionAccident
Indicates that an accident or unintended harmful event occurred during the course of a mission or operation.
- 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_69eff6eb30388190b898b96c4be6f49d |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f64bd68ac08190b35887261657a408 |
completed | May 2, 2026, 7:09 p.m. |
| PD | Predicate disambiguation | batch_69f641e2f1708190b45b48d6a43c51d2 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 28, 2026, 12:37 a.m.