Triple
T182367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States Naval Vessel Register (stricken after sinking) |
E3904
|
entity |
| Predicate | recordType |
P2554
|
FINISHED |
| Object | historical status record |
—
|
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: historical status record | Statement: [United States Naval Vessel Register (stricken after sinking), recordType, historical status record]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recordType Context triple: [United States Naval Vessel Register (stricken after sinking), recordType, historical status record]
-
A.
recordHeld
Indicates that one entity possesses or maintains a particular record associated with another entity or context.
-
B.
hasRecordType
chosen
Indicates that an entity is associated with or classified under a specific type or category of record.
-
C.
trackType
Indicates the specific kind or category of track associated with an entity, such as its functional or physical classification.
-
D.
formOfRecognition
Indicates a relationship where one entity serves as an official acknowledgment, honor, or validation granted to another entity.
-
E.
standardType
Indicates that one entity is classified as the standard, canonical, or reference type for another entity or context.
- 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_69a25497e2f08190a040f8c6e1842643 |
completed | Feb. 28, 2026, 2:36 a.m. |
| NER | Named-entity recognition | batch_69a2592516748190a85ae58eec191f14 |
completed | Feb. 28, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69a2566dfc388190988b1b42d5daaafe |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:40 a.m.