Triple
T11818609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johnston Atoll Chemical Agent Disposal System |
E281065
|
entity |
| Predicate | destroyedMunitionsType |
P29553
|
FINISHED |
| Object | artillery shells |
—
|
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: artillery shells | Statement: [Johnston Atoll Chemical Agent Disposal System, destroyedMunitionsType, artillery shells]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: destroyedMunitionsType Context triple: [Johnston Atoll Chemical Agent Disposal System, destroyedMunitionsType, artillery shells]
-
A.
ammunitionType
Indicates the specific kind or category of ammunition associated with or used by an entity.
-
B.
weaponTypeDelivered
Indicates that a specific type of weapon has been delivered from one entity to another.
-
C.
typicalOrdnance
chosen
Indicates that something is a standard or commonly used type of weaponry or munitions associated with a given entity or context.
-
D.
typeOfDestruction
Indicates the specific manner or method by which something is destroyed or caused to cease to exist.
-
E.
countryDestroyedStockpiles
Indicates that a country has eliminated or rendered unusable its existing stockpiles of a particular item, resource, or weapon.
- 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_69d6ab26aae88190b2489efcb2a24234 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a5e760988190b50d13bba5ef5b43 |
completed | April 10, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69d8a251fc08819095933f1d13c3b742 |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:42 p.m.