Triple
T35907603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | J 32E Lansen |
E1038513
|
entity |
| Predicate | roleConversion |
P172306
|
FINISHED |
| Object | converted from earlier Lansen variants |
—
|
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: converted from earlier Lansen variants | Statement: [J 32E Lansen, roleConversion, converted from earlier Lansen variants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleConversion Context triple: [J 32E Lansen, roleConversion, converted from earlier Lansen variants]
-
A.
roleConversionFrom
chosen
Indicates a transformation or mapping from one role or role type to another, specifying the original role in a role-conversion process.
-
B.
covertRole
Indicates that an entity holds or performs a hidden, secret, or undercover role in relation to another entity or context.
-
C.
exportRole
Indicates that an entity functions in a capacity or role specifically related to exporting goods, services, or data.
-
D.
roleAfterConversion
Indicates the role or position an entity holds after undergoing a conversion, transition, or change from a previous state or role.
-
E.
usesRoleShift
Indicates that an entity adopts or switches into another role or perspective, often temporarily, within a given context or interaction.
- 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_69f76e2259608190bf6788a132e0d139 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aa6fd79c8190b1a70068ace78068 |
completed | May 3, 2026, 8:05 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d435288190b30b1991fb003121 |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:07 p.m.