Triple
T4611055
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cheyenne Mountain Complex |
E100556
|
entity |
| Predicate | hardenedAgainst |
P20750
|
FINISHED |
| Object | chemical attack |
—
|
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: chemical attack | Statement: [Cheyenne Mountain Complex, hardenedAgainst, chemical attack]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hardenedAgainst Context triple: [Cheyenne Mountain Complex, hardenedAgainst, chemical attack]
-
A.
providesProtectionAgainst
Indicates that one entity serves to guard, shield, or defend another entity from a specified harm, threat, or adverse effect.
-
B.
hardness
Indicates the degree to which one entity resists being scratched, indented, or deformed by another.
-
C.
designedToWithstand
chosen
Indicates that something has been intentionally created or engineered to resist, endure, or remain functional under specified conditions, forces, or stresses.
-
D.
designedToDefeat
Indicates that one entity is intentionally created or configured with the purpose of overcoming, neutralizing, or rendering ineffective another entity.
-
E.
wasFortifiedBy
Indicates that a place or structure received defensive strengthening or fortification through the actions or resources of a specified agent or entity.
- 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_69bd43cce1e08190a07d53af6a9b6c24 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd59bffbf08190b13ef0810e6f9d19 |
completed | March 20, 2026, 2:29 p.m. |
| PD | Predicate disambiguation | batch_69bd522e2d5c8190937d0b5574f78f99 |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:12 p.m.