Triple
T27299422
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lockheed XP-58 Chain Lightning |
E688862
|
entity |
| Predicate | intendedRoleChange |
P63410
|
FINISHED |
| Object | from bomber destroyer to ground‑attack aircraft |
—
|
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: from bomber destroyer to ground‑attack aircraft | Statement: [Lockheed XP-58 Chain Lightning, intendedRoleChange, from bomber destroyer to ground‑attack aircraft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intendedRoleChange Context triple: [Lockheed XP-58 Chain Lightning, intendedRoleChange, from bomber destroyer to ground‑attack aircraft]
-
A.
redefinedRoleOf
chosen
Indicates that one entity has changed, updated, or newly specified the function, responsibilities, or position of another entity.
-
B.
interchangeRole
Indicates that two entities exchange or swap their roles or functional positions with each other.
-
C.
mayChangeTo
Indicates that one state, condition, or value is allowed or able to transition into another.
-
D.
changeDescription
Indicates that an entity’s descriptive information has been modified from a previous state.
-
E.
changeAgent
Indicates that an entity is responsible for causing or initiating a change in another entity or state.
- 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_69ef355a96308190a2bed991525fb278 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 27, 2026, 11:21 a.m.