Triple
T18520714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USRA Light Santa Fe 2-10-2 |
E452574
|
entity |
| Predicate | hasArticulatedFrame |
P57568
|
FINISHED |
| Object | no |
—
|
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: no | Statement: [USRA Light Santa Fe 2-10-2, hasArticulatedFrame, no]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasArticulatedFrame Context triple: [USRA Light Santa Fe 2-10-2, hasArticulatedFrame, no]
-
A.
testArticulated
Indicates that an articulated mechanism, structure, or component has been examined or evaluated, typically to verify its movement, function, or performance.
-
B.
articulatedWith
chosen
Indicates that two parts are connected by a joint or mechanism that allows controlled movement between them.
-
C.
hasArticulation
Indicates that one entity possesses or exhibits a specific type or structure of articulation in relation to another entity or system.
-
D.
hasArticulationType
Indicates the specific manner or type of connection or joint by which two parts or entities are linked or articulated.
-
E.
articulated
Indicates that one entity has expressed, formulated, or clearly stated another entity (such as an idea, plan, or position) in words or another communicative form.
- 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_69d8d386df84819092355ebb260d848e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5338db5e4819086503a2176dfe499 |
completed | April 19, 2026, 7:57 p.m. |
| PD | Predicate disambiguation | batch_69e469e0025c81908f16ed4f922674af |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 11:37 a.m.