Triple
T9457380
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Roe (DD-418) |
E228051
|
entity |
| Predicate | classCharacteristic |
P56672
|
FINISHED |
| Object | fast destroyer |
—
|
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: fast destroyer | Statement: [USS Roe (DD-418), classCharacteristic, fast destroyer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: classCharacteristic Context triple: [USS Roe (DD-418), classCharacteristic, fast destroyer]
-
A.
catalogCharacteristic
Indicates that a catalog has a specific characteristic or attribute associated with it.
-
B.
dataCharacteristic
Indicates that one entity specifies a property, attribute, or feature that characterizes a given piece of data.
-
C.
describesCharacteristicOf
chosen
Indicates that one entity expresses or specifies a characteristic, feature, or property of another entity.
-
D.
managementCharacteristic
Indicates a defining quality, style, or attribute associated with how something is managed or administered.
-
E.
projectCharacteristics
Indicates the defining features, qualities, or attributes that characterize a particular project.
- 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_69ca843b123881909b0e60028475d12d |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd7f90cf648190ab238ba6b4f03c4f |
completed | April 1, 2026, 8:26 p.m. |
| PD | Predicate disambiguation | batch_69cca55caaa8819089c5138e014892d3 |
completed | April 1, 2026, 4:55 a.m. |
Created at: March 30, 2026, 7:52 p.m.