Triple
T33584458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark 39 nuclear bomb |
E860241
|
entity |
| Predicate | safetyDeviceStatusInAccident |
P178656
|
FINISHED |
| Object | three of four safety mechanisms failed on one bomb |
—
|
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: three of four safety mechanisms failed on one bomb | Statement: [Mark 39 nuclear bomb, safetyDeviceStatusInAccident, three of four safety mechanisms failed on one bomb]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: safetyDeviceStatusInAccident Context triple: [Mark 39 nuclear bomb, safetyDeviceStatusInAccident, three of four safety mechanisms failed on one bomb]
-
A.
registrationStatusAfterAccident
Indicates the state of an entity’s registration following the occurrence of an accident.
-
B.
accidentState
Indicates the condition or status of an accident at a given point in time.
-
C.
involvedInAccident
Indicates that an entity participated in, was affected by, or was otherwise a party to a specific accident or collision event.
-
D.
hasAccidentAt
Indicates that an accident involving a subject occurs at a specific location or time.
-
E.
safetyOutcome
Indicates the resulting condition or consequence related to safety that arises from an action, event, or situation.
- 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_69f3497e70e48190951c94d072879bec |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f713bfdc148190a249a7874320bab8 |
completed | May 3, 2026, 9:22 a.m. |
| PD | Predicate disambiguation | batch_69f7127884388190884f23d181a65d19 |
completed | May 3, 2026, 9:16 a.m. |
| PDg | Predicate description generation | batch_69f7135fa2988190a20a94cfe616d754 |
completed | May 3, 2026, 9:20 a.m. |
Created at: May 1, 2026, 1:40 a.m.