Triple
T33584488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | W62 warhead |
E860242
|
entity |
| Predicate | designYield |
P197747
|
FINISHED |
| Object | approximately 170 kilotons of TNT |
—
|
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: approximately 170 kilotons of TNT | Statement: [W62 warhead, designYield, approximately 170 kilotons of TNT]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: designYield Context triple: [W62 warhead, designYield, approximately 170 kilotons of TNT]
-
A.
designOutcome
Indicates the result, effect, or consequence produced by a particular design or design process.
-
B.
designUse
Indicates that one entity is used as a design basis, purpose, or intended functional use for another entity.
-
C.
designLead
Indicates that one entity serves as the primary designer or person in charge of leading the design work for another entity or project.
-
D.
designSelectedIn
Indicates that a particular design has been chosen or picked out within a specific context, set, or selection process.
-
E.
designCheck
Indicates that an entity performs a review or verification of a design to ensure it meets specified requirements or standards.
- F. None of above. chosen
Provenance (4 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_69f3497e70e48190951c94d072879bec |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fea5e828cc8190a9b755a645dc56d2 |
completed | May 9, 2026, 3:11 a.m. |
| PD | Predicate disambiguation | batch_69fea36443f08190b2aced9b4a0525fd |
completed | May 9, 2026, 3 a.m. |
| PDg | Predicate description generation | batch_69fea5e75a5481908a04d91ee7255ebb |
completed | May 9, 2026, 3:11 a.m. |
Created at: May 1, 2026, 1:40 a.m.