Triple
T24724663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MH-68 Stingray |
E612410
|
entity |
| Predicate | tailCodePattern |
P157042
|
FINISHED |
| Object | USCG MH-68 series markings |
—
|
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: USCG MH-68 series markings | Statement: [MH-68 Stingray, tailCodePattern, USCG MH-68 series markings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tailCodePattern Context triple: [MH-68 Stingray, tailCodePattern, USCG MH-68 series markings]
-
A.
tailCodePrefix
Indicates that one entity’s tail code begins with, or is prefixed by, the string represented by the other entity.
-
B.
tailcodeExample
Indicates that a specific tailcode is provided as an example instance or illustration of that tailcode designation.
-
C.
segmentCode
Indicates a code that identifies or classifies a specific segment within a larger structure, sequence, or process.
-
D.
maskPattern
Indicates a relationship where one entity serves as a masking template or pattern that determines which parts or aspects of another entity are revealed, hidden, or transformed.
-
E.
typicalTrackCode
Indicates that one entity is the standard or commonly used track code associated with another entity.
- F. None of above. chosen
Provenance (4 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_69e2d7d6e7a48190bb43b0d8bb1137a0 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f410fe3b848190ae296a29f742ee30 |
completed | May 1, 2026, 2:33 a.m. |
| PD | Predicate disambiguation | batch_69f40ee8ada8819089a7016b50308ff0 |
completed | May 1, 2026, 2:24 a.m. |
| PDg | Predicate description generation | batch_69f410fc18808190b4e47d5a71d3a126 |
completed | May 1, 2026, 2:33 a.m. |
Created at: April 18, 2026, 3:42 a.m.