Triple
T38659062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northrop A-17 |
E939977
|
entity |
| Predicate | designationByUSArmyAirCorps |
P7137
|
FINISHED |
| Object | A-17 |
—
|
NE NERFINISHED |
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: A-17 | Statement: [Northrop A-17, designationByUSArmyAirCorps, A-17]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: designationByUSArmyAirCorps Context triple: [Northrop A-17, designationByUSArmyAirCorps, A-17]
-
A.
operatorRoleUSAAF
Indicates that an entity served in an operator role within the United States Army Air Forces (USAAF) in relation to another entity or activity.
-
B.
airForceDesignation
chosen
Indicates that one entity is the official designation or code assigned to something by an air force.
-
C.
airForceDesignationUser
Indicates that an entity uses or is assigned a specific air force designation.
-
D.
airForceEquivalent
Indicates that one military unit, rank, or asset is the corresponding or analogous counterpart within an air force to another entity in a different branch or context.
-
E.
designationByUSMC
Indicates that an entity has been formally assigned a specific designation or identifier by the United States Marine Corps (USMC).
- 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_69f76ede49648190a48bfe47032a05a3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ffb69812808190a751853b30183e65 |
completed | May 9, 2026, 10:35 p.m. |
| PD | Predicate disambiguation | batch_69ffb63bdda88190a9dd8426dc0bad43 |
completed | May 9, 2026, 10:33 p.m. |
Created at: May 3, 2026, 4:33 p.m.