Triple
T19107107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nevsky Express |
E467683
|
entity |
| Predicate | 2009AccidentCause |
P1788
|
FINISHED |
| Object | bomb explosion on the track |
—
|
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: bomb explosion on the track | Statement: [Nevsky Express, 2009AccidentCause, bomb explosion on the track]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 2009AccidentCause Context triple: [Nevsky Express, 2009AccidentCause, bomb explosion on the track]
-
A.
causedAccident
Indicates that one entity is responsible for bringing about or initiating an accident involving another entity or situation.
-
B.
accidentType
chosen
Indicates the specific category or kind of accident associated with an event or incident.
-
C.
accident
Indicates an unintended, unforeseen event or mishap occurring, often resulting in damage, injury, or disruption.
-
D.
resultOfAccident
Indicates that something exists or occurs as a consequence or outcome of an accident.
-
E.
accidentSequenceFeature
Indicates that one event or condition functions as a feature or component within the ordered sequence of circumstances leading to an accident.
- 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e391245c8190b1393577b61c4f76 |
completed | April 20, 2026, 8:28 a.m. |
| PD | Predicate disambiguation | batch_69e4b9ac41848190afd0f33b42cebe99 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:04 p.m.