Triple
T12212727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aberdeen Chemical Agent Disposal Facility |
E291003
|
entity |
| Predicate | typeOfStockpile |
P101027
|
FINISHED |
| Object | bulk mustard agent |
—
|
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: bulk mustard agent | Statement: [Aberdeen Chemical Agent Disposal Facility, typeOfStockpile, bulk mustard agent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfStockpile Context triple: [Aberdeen Chemical Agent Disposal Facility, typeOfStockpile, bulk mustard agent]
-
A.
typeOfWeaponsStockpile
chosen
Indicates that one entity specifies the kind or category of weapons contained within another entity’s stockpile.
-
B.
stockType
Indicates the classification or category of a stock (such as common, preferred, or another type) associated with an entity.
-
C.
storeType
Indicates the category or kind of store associated with an entity, such as its retail or service type.
-
D.
typeOfReserve
Indicates that one entity is classified as a specific kind or category of reserve in relation to another entity.
-
E.
stockpileShareDestroyed
Indicates that a portion of a stockpile has been eliminated or rendered unusable.
- 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_69d6ab65923081909acfc61b7a612233 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d920e312708190b4aede2e21f5f697 |
completed | April 10, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69d91c3d669c81908eea7ad61122d275 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:51 p.m.