Triple
T15016155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | W88 thermonuclear warhead |
E377963
|
entity |
| Predicate | detonationType |
P100269
|
FINISHED |
| Object | airburst or surface burst (mission-dependent) |
—
|
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: airburst or surface burst (mission-dependent) | Statement: [W88 thermonuclear warhead, detonationType, airburst or surface burst (mission-dependent)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: detonationType Context triple: [W88 thermonuclear warhead, detonationType, airburst or surface burst (mission-dependent)]
-
A.
detonationMode
Indicates the specific manner or mechanism by which a detonation is initiated or carried out in relation to an explosive event.
-
B.
detonationMethod
Indicates the method or mechanism by which an explosive device is triggered or detonated.
-
C.
explosionType
chosen
Indicates the specific kind or category of explosion associated with an event or entity.
-
D.
detonationCondition
Indicates the specific circumstances or triggers under which a detonation occurs or is initiated.
-
E.
detonationDepth
Indicates the depth or distance from a reference point at which a detonation occurs.
- 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7633fcc8190b2231f43252bc46f |
completed | April 15, 2026, 12:10 a.m. |
| PD | Predicate disambiguation | batch_69de9a6531a88190acde65199a477350 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:55 a.m.