Triple
T24536930
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MH-60T Jayhawk |
E606973
|
entity |
| Predicate | hasVariantDesignation |
P455
|
FINISHED |
| Object | HH-60J Jayhawk predecessor |
—
|
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: HH-60J Jayhawk predecessor | Statement: [MH-60T Jayhawk, hasVariantDesignation, HH-60J Jayhawk predecessor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVariantDesignation Context triple: [MH-60T Jayhawk, hasVariantDesignation, HH-60J Jayhawk predecessor]
-
A.
hasInternalDesignationFor
Indicates that one entity assigns or uses an internal label, code, or designation to refer to another entity.
-
B.
hasVariant
chosen
Indicates that one entity exists as an alternative form, version, or variation of another entity.
-
C.
hasDifferentDesignsFor
Indicates that one entity provides or uses multiple distinct designs tailored for different other entities or contexts.
-
D.
hasKVDesignation
Indicates that an entity has been assigned a specific KV (classification or designation) label or code.
-
E.
hasVariantIdentifications
Indicates that an entity is associated with one or more alternative identifications or versions that differ in some defined way from a primary identification.
- 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_69e2c4c90c848190b23c4303620dcaaf |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b0ca8081908d931aec560eae56 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:26 a.m.