Triple
T114151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zyklon B |
E2306
|
entity |
| Predicate | activationMethod |
P859
|
FINISHED |
| Object | opening of canisters in enclosed spaces |
—
|
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: opening of canisters in enclosed spaces | Statement: [Zyklon B, activationMethod, opening of canisters in enclosed spaces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: activationMethod Context triple: [Zyklon B, activationMethod, opening of canisters in enclosed spaces]
-
A.
appointmentMethod
Indicates how an appointment is arranged, such as the channel, process, or means used to schedule it.
-
B.
assessmentMethod
Indicates the method or procedure used to evaluate, measure, or judge something.
-
C.
securityType
Indicates the classification or category of security associated with an entity, such as the type of financial instrument, protection mechanism, or access control applied.
-
D.
securityMechanism
Indicates a relationship where one entity serves as a means or method to protect another entity from threats, vulnerabilities, or unauthorized actions.
-
E.
method
chosen
Indicates the technique, procedure, or process used by an entity to perform an action or achieve a result.
- 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_69a24fcdaeb48190a2d796677e4b3281 |
completed | Feb. 28, 2026, 2:15 a.m. |
| NER | Named-entity recognition | batch_69a25760af348190bf402089c240887d |
completed | Feb. 28, 2026, 2:48 a.m. |
| PD | Predicate disambiguation | batch_69a2564417848190a8a8a38e97348963 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:20 a.m.