Triple
T27938289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SouthJet Flight 227 |
E700670
|
entity |
| Predicate | depictedCauseOfAccident |
P170389
|
FINISHED |
| Object | mechanical failure |
—
|
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: mechanical failure | Statement: [SouthJet Flight 227, depictedCauseOfAccident, mechanical failure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictedCauseOfAccident Context triple: [SouthJet Flight 227, depictedCauseOfAccident, mechanical failure]
-
A.
causedAccident
Indicates that one entity is responsible for bringing about or initiating an accident involving another entity or situation.
-
B.
resultOfAccident
Indicates that something exists or occurs as a consequence or outcome of an accident.
-
C.
accidentType
Indicates the specific category or kind of accident associated with an event or incident.
-
D.
involvedInAccident
Indicates that an entity participated in, was affected by, or was otherwise a party to a specific accident or collision event.
-
E.
accident
Indicates an unintended, unforeseen event or mishap occurring, often resulting in damage, injury, or disruption.
- F. None of above. chosen
Provenance (4 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_69ef6a5028108190a14696d9821dde49 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f69063edbc81909e7735954aabee0b |
completed | May 3, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_69f68b78f29481908cc8f390496dee97 |
completed | May 2, 2026, 11:40 p.m. |
| PDg | Predicate description generation | batch_69f68f6584a88190a8c4d95c0c84bee9 |
completed | May 2, 2026, 11:57 p.m. |
Created at: April 27, 2026, 7:15 p.m.